A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

Shaoxiong JiShirui PanErik CambriaPekka MarttinenPhilip S. Yu

article2020IEEE TNNLS2,916 citations

Systematizes knowledge graph research through a structured taxonomy spanning representation learning, automated knowledge acquisition, and real-world applications while highlighting key open-source resources and future research directions.

Listen

Knowledge graphs represent structured facts about entities and their relationships, enabling artificial intelligence systems to perform reasoning tasks that mimic aspects of human cognition. The field has grown rapidly since Google’s 2012 launch of its Knowledge Graph, yet research remains scattered across representation techniques, data acquisition methods, temporal modeling, and downstream uses, making it difficult for practitioners to identify the most effective approaches or spot gaps.

This survey set out to deliver a single, structured overview of the entire knowledge-graph literature, introducing consistent taxonomies for representation learning, completion and extraction tasks, temporal extensions, and real-world applications while cataloguing datasets and open-source tools.

The authors reviewed several hundred papers published through early 2021, grouping methods according to their mathematical foundations (vector spaces, complex numbers, manifolds, Gaussian distributions), scoring functions (distance-based versus similarity-based), encoding architectures (linear, bilinear, convolutional, recurrent, graph neural, and transformer-based), and use of auxiliary signals such as text or images. They applied the same systematic lens to knowledge-graph completion via embeddings, path reasoning, and logical rules; to entity and relation discovery from text; and to temporal and application-oriented work.

The review shows that embedding models have matured from simple translation-based approaches to expressive architectures that capture symmetry, hierarchy, and uncertainty, yet they still struggle with long-range logical inference. Hybrid systems that combine embeddings with explicit rules or reinforcement-learned paths improve both accuracy and interpretability. Neural encoders now dominate relation extraction, while graph-aware language models and path-reasoning agents are beginning to deliver measurable gains on question answering and recommendation tasks. A curated collection of benchmark datasets and libraries is provided to lower the barrier for new experiments.

These findings matter because knowledge graphs underpin search engines, conversational agents, drug-discovery platforms, and enterprise data integration; clearer maps of what works reduce duplicated effort and speed deployment of reliable systems. The survey also highlights open challenges—scalable complex reasoning, unified frameworks that treat text and graphs together, interpretability, and automatic maintenance of evolving graphs—that must be addressed before knowledge-graph technology can support robust, large-scale cognitive applications.

Aalto University Monash University Nanyang Technological University University of Illinois Chicago bipartite graphs common-sense inference knowledge graphs knowledge representation knowledge acquisition tasks

arXiv: 2002.00388 shaoxiongji/knowledge-graphs

Paper: Translating Embeddings for Modeling Multi-relational Data, Antoine Bordes et al. (2013). Translating Embeddings for Modeling Multi-relational Data introduces TransE, the foundational translation-based knowledge graph embedding model heavily analyzed in the source survey.
Paper: Knowledge Graph Embedding by Translating on Hyperplanes, Zhen Wang et al. (2014). Knowledge Graph Embedding by Translating on Hyperplanes presents TransH, directly establishing the foundational hyperplane-translation approach reviewed in the source's representation section.
Paper: Modeling Relational Data with Graph Convolutional Networks, Michael Schlichtkrull et al. (2018). Modeling Relational Data with Graph Convolutional Networks introduces R-GCNs, the primary network architecture detailed in the source survey for knowledge graph completion and link prediction.
Paper: A Comprehensive Survey on Graph Neural Networks, Zonghan Wu et al. (2019). A Comprehensive Survey on Graph Neural Networks establishes the broader graph deep learning foundations that the source survey builds upon when analyzing graph-based representation learning.

Paper: Retrieval-Augmented Generation for Large Language Models: A Survey, Yunfan Gao et al. (2023). Retrieval-Augmented Generation for Large Language Models: A Survey extends the source survey by exploring how modern knowledge-intensive architectures integrate external knowledge graphs and retrieval systems.

Cover for A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

Abstract

Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey, we provide a comprehensive review of knowledge graph covering overall research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models, and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning, are reviewed. We further explore several emerging topics, including meta relational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of datasets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.

I Introduction
II Overview
II-A A Brief History of Knowledge Bases
II-B Definitions and Notations
II-C Categorization of Research on Knowledge Graph
II-D Related Surveys
III Knowledge Representation Learning
III-A Representation Space
III-A1 Point-Wise Space
III-A2 Complex Vector Space
III-A3 Gaussian Distribution
III-A4 Manifold and Group
III-B Scoring Function
III-B1 Distance-based Scoring Function
III-B2 Semantic Matching
III-C Encoding Models
III-C1 Linear/Bilinear Models
III-C2 Factorization Models
III-C3 Neural Networks
III-C4 Convolutional Neural Networks
III-C5 Recurrent Neural Networks
III-C6 Transformers
III-C7 Graph Neural Networks (GNNs)
III-D Embedding with Auxiliary Information
III-D1 Textual Description
III-D2 Type Information
III-D3 Visual Information
III-D4 Uncertain Information
III-E Summary
IV Knowledge Acquisition
IV-A Knowledge Graph Completion
IV-A1 Embedding-based Models
IV-A2 Relation Path Reasoning
IV-A3 RL-based Path Finding
IV-A4 Rule-based Reasoning
IV-A5 Meta Relational Learning
IV-A6 Triple Classification
IV-B Entity Discovery
IV-B1 Entity Recognition
IV-B2 Entity Typing
IV-B3 Entity Disambiguation
IV-B4 Entity Alignment
IV-C Relation Extraction
IV-C1 Neural Relation Extraction
IV-C2 Attention Mechanism
IV-C3 Graph Convolutional Networks (GCNs)
IV-C4 Adversarial Training
IV-C5 Reinforcement Learning
IV-C6 Other Advances
IV-C7 Joint Entity and Relation Extraction
IV-D Summary
V Temporal Knowledge Graph
V-A Temporal Information Embedding
V-B Entity Dynamics
V-C Temporal Relational Dependency
V-D Temporal Logical Reasoning
VI Knowledge-Aware Applications
VI-A Language Representation Learning
VI-B Question Answering
VI-B1 Single-fact QA
VI-B2 Multi-hop Reasoning
VI-C Recommender Systems
VII Future Directions
VII-A Complex Reasoning
VII-B Unified Framework
VII-C Interpretability
VII-D Scalability
VII-E Knowledge Aggregation
VII-F Automatic Construction and Dynamics
VIII Conclusion
A A Brief History of Knowledge Bases
B Mathematical Operations
C A Summary of KRL Models
D KRL Model Training
D-A Open and Closed World Assumption
D-B Loss Function
D-C Negative Sampling
E More Knowledge-aware Applications
E-A Text Classification and Task-Specific Applications
E-B Dialogue Systems
E-C Medicine and Biology
E-D Other Applications
F Datasets and Libraries
F-A Datasets
F-A1 General Datasets
F-A2 Domain-Specific Datasets
F-A3 Task-Specific Datasets
F-B Open-Source Libraries
References

Knowls

Knowl 1 — Taxonomy and Conceptual Workflow of Knowledge Representation Learning
model/method
The design of a Knowledge Representation Learning (KRL) or Knowledge Graph Embedding (KGE) model is structured around four fundamental scopes:
1. Representation Space: The geometric or algebraic space in which entities $\mathcal{E}$ and relations $\mathcal{R}$ are embedded. Options include real-valued pointwise Euclidean vector spaces $\mathbb{R}^d$ , complex vector spaces $\mathbb{C}^d$ , hypercomplex quaternion spaces $\mathbb{H}^d$ , Gaussian probability distributions $\mathcal{N}(\mu, \Sigma)$ , hyperbolic Riemannian manifolds $\mathbb{B}_c^d$ , and group/manifold structures (such as the Lie group torus $\mathbb{T}^n$ or Dihedral symmetry groups $D_K$ ).
2. Scoring Function: The algebraic or geometric metric $f_r(h, t)$ measuring the plausibility or energy of a factual triple $(h, r, t)$ . These primarily branch into translational distance-based scoring (penalizing deviations from relational translations, e.g., $h + r \approx t$ ) and semantic similarity matching (computing bilinear or tensor compositions, e.g., $h^\top M_r t$ ).
3. Encoding Models: The architectural mechanisms that capture compositional interactions between entities and relations. These span linear and bilinear transformations, tensor factorization techniques (such as canonical polyadic decomposition, Tucker decomposition, and LowFER), and deep neural architectures (multilayer perceptrons, convolutional networks like ConvE/ConvKB, recurrent architectures like RSN, Transformer encoders like CoKE/KG-BERT, and relational graph convolutional networks like R-GCN and CompGCN).
4. Auxiliary Information Integration: Incorporating multimodal and external context into embeddings, including entity textual descriptions, hierarchical semantic type constraints, visual entity images, relation paths, and uncertainty confidence scores.
Knowl 2 — Mathematical Formulations of Knowledge Graph Scoring Functions
equation
Knowledge graph embedding models measure the plausibility of a factual triple $(h, r, t)$ (where $h, t \in \mathcal{E}$ denote head and tail entities and $r \in \mathcal{R}$ denotes the relation) using scoring functions $f_r(h, t)$ , categorized into translational distance and semantic matching formulations:

Distance-based and Translational models:
- TransE: $f_r(h, t) = -\|h + r - t\|_{L_1 / L_2}$ , where $h, r, t \in \mathbb{R}^d$ .
- TransH: $f_r(h, t) = -\|(h - w_r^\top h w_r) + r - (t - w_r^\top t w_r)\|_2^2$ , with relation hyperplane normal vector $w_r \in \mathbb{R}^d$ .
- TransR: $f_r(h, t) = -\|M_r h + r - M_r t\|_2^2$ , with relation projection matrix $M_r \in \mathbb{R}^{k \times d}$ .
- TransD: $f_r(h, t) = -\|(r_p h_p^\top + I)h + r - (r_p t_p^\top + I)t\|_2^2$ , using dynamic projection vectors $h_p, t_p, r_p$ .
- RotatE: $f_r(h, t) = -\|h \circ r - t\|$ , where $h, r, t \in \mathbb{C}^d$ , $|r_i|=1$ , and $\circ$ represents the Hadamard product encoding complex rotation.
Semantic similarity, Bilinear, and Factorization models:
- DistMult: $f_r(h, t) = h^\top \operatorname{diag}(M_r) t$ , where $h, t \in \mathbb{R}^d$ and $M_r \in \mathbb{R}^d$ .
- ComplEx: $f_r(h, t) = \operatorname{Re}(\langle r, h, \bar{t} \rangle) = \operatorname{Re}\left(\sum_{k=1}^d r_k h_k \bar{t}_k\right)$ , where $h, r, t \in \mathbb{C}^d$ and $\bar{t}$ is the complex conjugate of $t$ .
- HolE: $f_r(h, t) = r^\top (h \star t)$ , where $\star$ denotes circular correlation $[a \star b]_k = \sum_{i=0}^{d-1} a_i b_{(k+i) \bmod d}$ .
- QuatE: $f_r(h, t) = \frac{h \otimes r}{|r|} \cdot t$ , where $h, r, t \in \mathbb{H}^d$ and $\otimes$ denotes the Hamilton product.
- TuckER: $f_r(h, t) = \mathcal{W} \times_1 h \times_2 r \times_3 t$ , where $\mathcal{W} \in \mathbb{R}^{d_e \times d_r \times d_e}$ is a core tensor and $\times_n$ denotes the tensor product along the $n$ -th mode.
- ConvE: $f_r(h, t) = \sigma(\operatorname{vec}(\sigma([M_h; M_r] * \omega)) W) t$ , where $M_h, M_r \in \mathbb{R}^{d_w \times d_h}$ are 2D reshaped embedding matrices, $*$ is 2D convolution with filter $\omega$ , and $W$ is a linear transformation matrix.
Knowl 3 — Non-Euclidean and Geometric Representation Spaces for Knowledge Graphs
model/method
To overcome the expressiveness limitations of Euclidean vector spaces $\mathbb{R}^d$ , alternative embedding spaces are utilized:
1. Complex and Hypercomplex Spaces: ComplEx embeds entities and relations into $\mathbb{C}^d$ using Hermitian dot products $\langle h, t \rangle = \bar{h}^\top t$ to model symmetric and antisymmetric relations. RotatE defines relations as element-wise rotations $t = h \circ r$ ( $|r_i| = 1$ ) via Euler's identity $e^{i\theta} = \cos \theta + i \sin \theta$ , capturing symmetry, antisymmetry, inversion, and composition. QuatE extends representations to the quaternion hypercomplex space $\mathbb{H}^d = \{a + bi + cj + dk\}$ using the Hamilton product $h \otimes r$ to capture four-dimensional relational cross-dependencies.
2. Manifold and Hyperbolic Spaces: ManifoldE expands point-wise embeddings to geometric manifolds (spheres or hyperplanes) defined by $M(h, r, t) \approx D_r^2$ . Hyperbolic Riemannian spaces (such as the Poincaré ball $\mathbb{B}_c^d = \{x \in \mathbb{R}^d : c\|x\|^2 < 1\}$ with curvature $-c < 0$ ) in MuRP and AttH naturally embed hierarchical structures and power-law degree distributions with low geometric distortion.
3. Group-Theoretic Spaces: TorusE addresses unbounded embedding growth in TransE by embedding into the compact Lie group $n$ -dimensional torus $\mathbb{T}^n = \mathbb{R}^n / \mathbb{Z}^n$ with distance $\min_{(x,y) \in ([h]+[r]) \times [t]} \|x - y\|$ . DihEdral employs the finite non-Abelian dihedral group $D_K$ using 2D block-diagonal matrices to preserve relation symmetry, skew-symmetry, inversion, and composition via reflection and 2D rotation operations.
4. Gaussian Density Spaces: KG2E and TransG map entities and relations to multi-dimensional Gaussian probability distributions $h \sim \mathcal{N}(\mu_h, \Sigma_h)$ and $t \sim \mathcal{N}(\mu_t, \Sigma_t)$ , where mean vectors denote semantic coordinates and covariance matrices model semantic uncertainty and concept broadness.
Knowl 4 — Training Assumptions, Loss Objectives, and Negative Sampling Strategies
model/method
Knowledge graph representation learning relies on training assumptions, loss functions, and negative sampling mechanisms:
1. World Assumptions:
- Closed World Assumption (CWA): Assumes all unobserved factual triples are false.
- Open World Assumption (OWA): Assumes unobserved triples can be either missing true facts or false facts, reflecting the incompleteness of knowledge graphs.
1. Optimization Loss Functions:
- Pairwise Margin-Based Ranking Loss: $\min_{\Theta} \sum_{(h,r,t) \in \mathcal{F}} \sum_{(h',r,t') \in \mathcal{F}'} \max(0, f_r(h,t) + \gamma - f_r(h', t'))$ where $\gamma > 0$ is a margin parameter, $\mathcal{F}$ is the set of observed positive triples, and $\mathcal{F}'$ is the set of corrupted negative triples.
- Logistic Loss: $\min_{\Theta} \sum_{(h,r,t) \in \mathcal{F} \cup \mathcal{F}'} \log(1 + \exp(-y_{hrt} \cdot f_r(h,t)))$ where $y_{hrt} \in \{1, -1\}$ denotes the triple label.
- Self-Adversarial Negative Sampling Loss: $L = -\log \sigma(\gamma - f_r(h,t)) - \sum_{i=1}^k p(h'_i, r, t'_i) \log \sigma(f_r(h'_i, t'_i) - \gamma)$
1. Negative Sampling Distributions:
- Uniform Sampling: Randomly replaces head or tail entities with equal probability $1/|\mathcal{E}|$ .
- Bernoulli Sampling: Sets the replacement probability of head vs. tail according to the relation mapping cardinality: $\frac{tph}{tph + hpt}$ , where $tph$ is the average number of tails per head and $hpt$ is the average number of heads per tail.
- Adversarial Sampling (KBGAN): Uses a generator network $f_G$ to produce negative samples with probability $p(h'_j, r, t'_j) = \frac{\exp f_G(h'_j, r, t'_j)}{\sum_k \exp f_G(h'_k, r, t'_k)}$ .
- Self-Adversarial Sampling: Weights negative candidates using the model's current scoring distribution: $p(h'_j, r, t'_j | \{(h_i, r_i, t_i)\}) = \frac{\exp(\alpha f(h'_j, r, t'_j))}{\sum_i \exp(\alpha f(h'_i, r, t'_i))}$ , where $\alpha$ is a sampling temperature.
Knowl 5 — Multi-Hop Relational Path Finding via Reinforcement Learning
model/method
Multi-hop relational reasoning over knowledge graphs can be formulated as a Markov Decision Process (MDP), where a policy gradient agent navigates across graph paths between entity pairs:
- State Space: The environment state $s_t$ at step $t$ encodes the current entity position $e_t$ , the query entity $e_q$ (or query relation $r_q$ ), and path history. Formulations include continuous state vector differences $s_t = (e_t, e_q - e_t)$ (DeepPath), explicit query tuples $s_t = (e_t, e_s, r_q, e_q)$ (MINERVA), or recurrent path encodings $s_t = (e_s, r_q, h_t)$ (CPL).
- Action Space: The action set $A_t$ consists of available outgoing edges and neighboring entities from $e_t$ : $A_t = \{(e_t, r, v) \in \mathcal{G}\}$ , augmented with an explicit self-loop or $\{STOP\}$ action to terminate search.
- Policy Network: Parameterized policy $\pi_\theta(a_t | s_t)$ selects actions using feedforward neural networks (FCN in DeepPath), recurrent units (LSTM in MINERVA and Multi-Hop), or Monte Carlo Tree Search controllers (M-Walk).
- Reward Formulation:
  1. Binary Terminal Reward: $\gamma = \mathbb{I}\{e_t = e_q\}$ , rewarding successful arrivals at the target entity.
  2. Path Efficiency Reward: Scaled inversely by path length, $\frac{1}{\text{length}(p)}$ , penalizing redundant loops.
  3. Path Diversity Reward: $-\frac{1}{|\mathcal{F}|} \sum_{i=1}^{|\mathcal{F}|} \cos(p, p_i)$ , encouraging distinct relational paths across training entity pairs.
  4. Continuous / Soft Reward: Uses continuous scores from pretrained embedding models $f_{r_q}(e_s, e_T)$ to alleviate sparse reward feedback.
Knowl 6 — Neuro-Symbolic and Rule-Based Reasoning for Knowledge Graph Completion
model/method
Neuro-symbolic knowledge graph completion couples distributed representation learning with symbolic first-order logical rules to provide interpretable, regularized, and sample-efficient inference. Logical rules follow Horn clause structures: $\text{head} \leftarrow \text{body}, \quad \text{e.g.,} \quad (Y, \text{sonOf}, X) \leftarrow (X, \text{hasChild}, Y) \wedge (Y, \text{gender}, \text{Male})$

Key integration frameworks include:
1. Fuzzy Logic Joint Embedding: Frameworks like KALE evaluate continuous $t$ -norm fuzzy logic compositions (conjunction, disjunction, and negation) over triple scores to evaluate complex formulas and jointly optimize embedding loss and logic rule satisfiability.
2. Iterative Rule Injection and Axiom Induction: Systems like RUGE and IterE alternate between generating soft pseudo-labels for unlabeled triples via mined soft rules, updating embeddings via labeled and pseudo-labeled triples, and inducing new logical axioms from embeddings.
3. Differentiable Rule Learning:
- Neural Theorem Provers (NTP): Formulate backward-chaining logical proofs with differentiable operators using radial basis function (RBF) kernel computations in continuous vector space.
- NeuralLP: Integrates neural controllers and memory architectures to perform inductive logic programming with end-to-end gradient-based optimization.
- Neural-Num-LP: Extends differentiable rule induction to learn numerical rules with dynamic programming and cumulative operations.
1. Probabilistic Logic Neural Networks: Models like pLogicNet and ExpressGNN combine Markov Logic Networks (MLNs) with Graph Neural Networks (GNNs), handling uncertainty in logical rules and scaling variational inference over large-scale knowledge graphs.
Knowl 7 — Meta Relational and Few-Shot Learning for Knowledge Graph Completion
model/method
Meta relational learning targets the long-tail distribution of relations and dynamic acquisition scenarios where link prediction must be performed for new or scarce relations given only a few support instances:
1. Metric-Based Approaches: Models such as GMatching use Relational Graph Convolutional Networks (R-GCN) to encode one-hop local subgraphs around entities, followed by multi-step metric matching with LSTM networks to compute similarity between support reference pairs and query pairs.
2. Optimization-Based Meta-Learning: Frameworks like Meta-KGR and MetaR employ model-agnostic meta-learning (MAML) principles. MetaR extracts relation-specific meta information from support sets and enables fast adaptation via gradient steps on high-order relational representations.
3. Generative Adversarial Zero-Shot Learning: Conditional Generative Adversarial Networks (GANs) synthesize plausible relational embeddings for completely unseen relations conditioned on text relation descriptions, bypassing the need for training triples.
4. Transductive Extrapolation: Graph Extrapolation Networks (GEN) perform transductive meta-learning for few-shot out-of-graph link prediction, propagating knowledge to newly emerged entities and unseen relations across connected subgraphs.
Knowl 8 — Neural Paradigms for Distantly Supervised Relation Extraction
model/method
Distantly supervised relation extraction heuristically aligns entity pairs from knowledge graphs to unstructured sentences to extract new relational triples, introducing labeling noise. Modern neural relation extraction (NRE) addresses this via several mechanisms:
1. Piecewise Convolutional Max Pooling: Piecewise CNN (PCNN) divides convolutional representation into three distinct segments based on head and tail entity mention boundaries, applying piecewise max pooling to capture intra-argument and contextual features.
2. Multi-Instance Selective Attention: Encodes sentence bags containing the same entity pairs, computing selective attention weights across sentences to suppress false positive matches.
3. Graph Convolutional Networks on Dependency Trees: Models like C-GCN and AGGCN encode sentence dependency parse trees using path-centric pruning or multi-head attention to focus on the shortest dependency paths between entity mentions.
4. Adversarial and Reinforcement Denoising: Adversarial architectures (DSGAN) train a generator to discover true positive instances and a discriminator to filter noise. Reinforcement learning models frame sentence selection as a policy search problem (using reward functions tied to F1 improvement or prediction certainty) to filter false positives into negative bags.
5. Joint Entity and Relation Extraction: Unifies entity tagging and relation extraction into single-stage architectures (e.g., sequence labeling schemes, multi-turn QA, cascading binary tagging, and token-pair linking like TPLinker) to eliminate pipeline error propagation and handle overlapping entity-relation triplets.
Knowl 9 — Entity Discovery Taxonomy: Recognition, Typing, Disambiguation, and Alignment
definition
Entity discovery comprises four core subtasks for identifying, categorizing, linking, and harmonizing entities across unstructured text and disparate knowledge graphs:
1. Named Entity Recognition (NER): The process of detecting and labeling named entity mentions in raw text into semantic categories (e.g., Person, Location, Organization), utilizing sequence models (BiLSTM-CRF), machine reading comprehension query formats, or knowledge-enhanced pretrained language encoders.
2. Entity Typing: The task of assigning fine-grained semantic categories or hierarchical types to entity mentions, framed as multi-class, multi-label classification over hierarchical ontology type trees using partial-label embedding or hierarchical prototype embeddings.
3. Entity Disambiguation (Entity Linking): The task of resolving ambiguous entity mentions in text to corresponding unique entity nodes within a knowledge graph, using local neural attention, semantic relatedness metrics, and joint entity-text embedding spaces.
4. Entity Alignment (Cross-Graph Alignment): The process of unifying identical entities across distinct knowledge graphs $\mathcal{G}_1 = (\mathcal{E}_1, \mathcal{R}_1, \mathcal{F}_1)$ and $\mathcal{G}_2 = (\mathcal{E}_2, \mathcal{R}_2, \mathcal{F}_2)$ by finding an alignment set $A = \{(e_1, e_2) \in \mathcal{E}_1 \times \mathcal{E}_2 \mid e_1 \equiv e_2\}$ seeded by initial known correspondences. Techniques include translation distance calibration $\|e_1 + r_{(\mathcal{E}_1 \to \mathcal{E}_2)} - e_2\|$ , linear transformations $\|M_{(\mathcal{E}_1 \to \mathcal{E}_2)} e_1 - e_2\|$ , iterative bootstrapping with alignment editing (BootEA), and cross-lingual multi-view attribute embeddings.
Knowl 10 — Temporal Knowledge Graph Representation and Dynamics
model/method
Temporal Knowledge Graphs (TKGs) incorporate temporal information to represent time-varying facts, extending static triples $(h, r, t)$ into temporal quadruples $(h, r, t, \tau)$ (where $\tau$ is a timestamp) or time-scoped intervals $(h, r, t, [\tau_s, \tau_e])$ (where $\tau_s$ and $\tau_e$ define validity bounds):
1. Temporal Information Embedding:
- TTransE: Extends translational distance with a timestamp vector $\tau$ , scoring via $f_\tau(h, r, t) = -\|h + r + \tau - t\|_{L_1 / L_2}$ .
- HyTE: Projects entity and relation embeddings onto a timestamp-specific hyperplane normal vector $w_\tau$ via $P_\tau(h) = h - (w_\tau^\top h)w_\tau$ , $P_\tau(t) = t - (w_\tau^\top t)w_\tau$ , and $P_\tau(r) = r - (w_\tau^\top r)w_\tau$ , with scoring function $f_\tau(h, r, t) = \|P_\tau(h) + P_\tau(r) - P_\tau(t)\|_{L_1/L_2}$ .
- TComplEx: Extends complex tensor decomposition to 4-order tensor completion $\mathcal{X} \in \mathbb{R}^{|\mathcal{E}| \times |\mathcal{R}| \times |\mathcal{E}| \times |\mathcal{T}|}$ with weighted $L_p$ regularization.
1. Entity and Event Dynamics: Frameworks such as Know-evolve utilize multivariate temporal point processes to model non-linear event occurrences and dynamic entity state vectors over continuous time. RE-NET combines recurrent event encoders with graph neighborhood aggregators to capture concurrent and historical temporal interactions.
2. Temporal Relational Dependencies: Models temporal sequence order among relations (e.g., $\text{wasBornIn} \to \text{graduateFrom} \to \text{workAt} \to \text{diedIn}$ ) by enforcing regularizations on relation transitions $f(\langle r_k, r_l \rangle) = \|r_k T - r_l\|_{L_1/L_2}$ , where $T \in \mathbb{R}^{d \times d}$ is an asymmetric temporal transition matrix optimized under integer linear programming constraints.
Knowl 11 — Knowledge-Aware Downstream Applications: Language Pretraining, QA, and Recommendations
model/method
Structured knowledge graph representations are incorporated into downstream machine learning applications across three core areas:
1. Knowledge-Enhanced Language Representation:
- Entity Masking and Integration: ERNIE and K-BERT inject entity embeddings and domain subgraphs directly into Transformer encoder layers using modified attention masks.
- Joint Pretraining Objectives: KEPLER jointly optimizes masked language modeling objectives and knowledge embedding translation losses (e.g., TransE) over a unified Transformer backbone.
- Contextual Knowledge Graphs: CoLAKE integrates language tokens and entity graph nodes into a unified word-knowledge graph encoded via modified Transformer attention.
1. Knowledge Graph Question Answering (KG-QA):
- Single-Fact QA: Resolves simple factoid questions by mapping question text to single KG triples using focused pruning (CFO) or bidirectional memory networks (BAMnet).
- Multi-Hop Commonsense QA: Bridges unstructured questions with multi-hop graph paths using external commonsense bases (ConceptNet). Frameworks like KagNet and CogQA extract cognitive reasoning subgraphs, encoding relational paths with GNNs, LSTMs, and hierarchical path attention to generate explanations and answers.
1. Knowledge-Aware Recommender Systems:
- Embedding-Based Regularization: Collaborative CKE combines translational knowledge embeddings, text autoencoders, and image features to enrich item representations.
- Multi-Task Feature Sharing: MKR alternates feature extraction between item recommendation networks and KG representation modules to capture high-order item-entity interactions.
- Path and Graph Propagation: KPRN processes user-item entity-relation paths via LSTM sequence modeling; PGPR uses reinforcement learning policy agents over user-item paths for explainable recommendations; and KGAT applies graph attention networks to propagate high-order collaborative embeddings across combined user-item and entity-relation graphs.

Coverage note — No substantial contributed conceptual categorization or mathematical formulation from the survey was omitted; standard introductory historical overviews and generic software library listings were summarized into the taxonomy and application knowls.

References

1.A. Newell, J. C. Shaw, and H. A. Simon, “Report on a general problem solving program,” in IFIP congress, vol. 256, 1959, p. 64.
2.E. Shortliffe, Computer-based medical consultations: MYCIN. Elsevier, 2012, vol. 2.
3.X. Dong, E. Gabrilovich, G. Heitz, W. Horn, N. Lao, K. Murphy, T. Strohmann, S. Sun, and W. Zhang, “Knowledge vault: A web-scale approach to probabilistic knowledge fusion,” in SIGKDD. ACM, 2014, pp. 601–610.
4.M. Nickel, K. Murphy, V. Tresp, and E. Gabrilovich, “A review of relational machine learning for knowledge graphs,” Proceedings of the IEEE, vol. 104, no. 1, pp. 11–33, 2016.
5.Q. Wang, Z. Mao, B. Wang, and L. Guo, “Knowledge graph embedding: A survey of approaches and applications,” IEEE TKDE, vol. 29, no. 12, pp. 2724–2743, 2017.
6.A. Hogan, E. Blomqvist, M. Cochez, C. d’Amato, G. de Melo, C. Gutierrez, J. E. L. Gayo, S. Kirrane, S. Neumaier, A. Polleres et al., “Knowledge graphs,” arXiv preprint arXiv:2003.02320, 2020.
7.F. N. Stokman and P. H. de Vries, “Structuring knowledge in a graph,” in Human-Computer Interaction, 1988, pp. 186–206.
8.A. Bordes, J. Weston, R. Collobert, and Y. Bengio, “Learning structured embeddings of knowledge bases,” in AAAI, 2011, pp. 301–306.
9.Y. Lin, X. Han, R. Xie, Z. Liu, and M. Sun, “Knowledge representation learning: A quantitative review,” arXiv preprint arXiv:1812.10901, 2018.
10.R. H. Richens, “Preprogramming for mechanical translation.” Mechanical Translation, vol. 3, no. 1, pp. 20–25, 1956.
11.H. Paulheim, “Knowledge graph refinement: A survey of approaches and evaluation methods,” Semantic web, vol. 8, no. 3, pp. 489–508, 2017.
12.L. Ehrlinger and W. Wöß, “Towards a definition of knowledge graphs,” SEMANTiCS (Posters, Demos, SuCCESS), vol. 48, pp. 1–4, 2016.
13.T. Wu, G. Qi, C. Li, and M. Wang, “A survey of techniques for constructing chinese knowledge graphs and their applications,” Sustainability, vol. 10, no. 9, p. 3245, 2018.
14.X. Chen, S. Jia, and Y. Xiang, “A review: Knowledge reasoning over knowledge graph,” Expert Systems with Applications, vol. 141, p. 112948, 2020.
15.T. Ebisu and R. Ichise, “TorusE: Knowledge graph embedding on a lie group,” in AAAI, 2018, pp. 1819–1826.
16.A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko, “Translating embeddings for modeling multi-relational data,” in NIPS, 2013, pp. 2787–2795.
17.Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu, “Learning entity and relation embeddings for knowledge graph completion,” in AAAI, 2015, pp. 2181–2187.
18.R. Socher, D. Chen, C. D. Manning, and A. Ng, “Reasoning with neural tensor networks for knowledge base completion,” in NIPS, 2013, pp. 926–934.
19.Z. Zhang, J. Cai, Y. Zhang, and J. Wang, “Learning hierarchy-aware knowledge graph embeddings for link prediction.” in AAAI, 2020, pp. 3065–3072.
20.Z. Wang, J. Zhang, J. Feng, and Z. Chen, “Knowledge graph embedding by translating on hyperplanes,” in AAAI, 2014, pp. 1112–1119.
21.M. Nickel, L. Rosasco, and T. Poggio, “Holographic embeddings of knowledge graphs,” in AAAI, 2016, pp. 1955–1961.
22.H. Liu, Y. Wu, and Y. Yang, “Analogical inference for multi-relational embeddings,” in ICML, 2017, pp. 2168–2178.
23.T. Trouillon, J. Welbl, S. Riedel, E. Gaussier, and G. Bouchard, “Complex embeddings for simple link prediction,” in ICML, 2016, pp. 2071–2080.
24.Z. Sun, Z.-H. Deng, J.-Y. Nie, and J. Tang, “RotatE: Knowledge graph embedding by relational rotation in complex space,” in ICLR, 2019, pp. 1–18.
25.S. Zhang, Y. Tay, L. Yao, and Q. Liu, “Quaternion knowledge graph embedding,” in NeurIPS, 2019, pp. 2731–2741.
26.S. He, K. Liu, G. Ji, and J. Zhao, “Learning to represent knowledge graphs with gaussian embedding,” in CIKM, 2015, pp. 623–632.
27.H. Xiao, M. Huang, and X. Zhu, “TransG: A generative model for knowledge graph embedding,” in ACL, vol. 1, 2016, pp. 2316–2325.
28.——, “From one point to a manifold: Orbit models for knowledge graph embedding,” in IJCAI, 2016, pp. 1315–1321.
29.I. Balazevic, C. Allen, and T. Hospedales, “Multi-relational poincare graph embeddings,” in NeurIPS, 2019, pp. 4463–4473.
30.I. Chami, A. Wolf, D.-C. Juan, F. Sala, S. Ravi, and C. Re, “Low-dimensional hyperbolic knowledge graph embeddings,” in ACL, 2020.
31.C. Xu and R. Li, “Relation embedding with dihedral group in knowledge graph,” in ACL, 2019, pp. 263–272.
32.B. Yang, W.-t. Yih, X. He, J. Gao, and L. Deng, “Embedding entities and relations for learning and inference in knowledge bases,” in ICLR, 2015, pp. 1–13.
33.G. Ji, S. He, L. Xu, K. Liu, and J. Zhao, “Knowledge graph embedding via dynamic mapping matrix,” in ACL-IJCNLP, vol. 1, 2015, pp. 687–696.
34.H. Xiao, M. Huang, Y. Hao, and X. Zhu, “TransA: An adaptive approach for knowledge graph embedding,” in AAAI, 2015, pp. 1–7.
35.J. Feng, M. Huang, M. Wang, M. Zhou, Y. Hao, and X. Zhu, “Knowledge graph embedding by flexible translation,” in KR, 2016, pp. 557–560.
36.Q. Xie, X. Ma, Z. Dai, and E. Hovy, “An interpretable knowledge transfer model for knowledge base completion,” in ACL, 2017, pp. 950–962.
37.W. Qian, C. Fu, Y. Zhu, D. Cai, and X. He, “Translating embeddings for knowledge graph completion with relation attention mechanism.” in IJCAI, 2018, pp. 4286–4292.
38.S. Yang, J. Tian, H. Zhang, J. Yan, H. He, and Y. Jin, “TransMS: knowledge graph embedding for complex relations by multidirectional semantics,” in IJCAI, 2019, pp. 1935–1942.
39.A. Bordes, X. Glorot, J. Weston, and Y. Bengio, “A semantic matching energy function for learning with multi-relational data,” Machine Learning, vol. 94, no. 2, pp. 233–259, 2014.
40.Y. Xue, Y. Yuan, Z. Xu, and A. Sabharwal, “Expanding holographic embeddings for knowledge completion,” in NeurIPS, 2018, pp. 4491–4501.
41.K. Hayashi and M. Shimbo, “On the equivalence of holographic and complex embeddings for link prediction,” in ACL, 2017, pp. 554–559.
42.W. Zhang, B. Paudel, W. Zhang, A. Bernstein, and H. Chen, “Interaction embeddings for prediction and explanation in knowledge graphs,” in WSDM, 2019, pp. 96–104.
43.D. Q. Nguyen, T. D. Nguyen, D. Q. Nguyen, and D. Phung, “A novel embedding model for knowledge base completion based on convolutional neural network,” in NAACL, 2018, pp. 327–333.
44.C. Shang, Y. Tang, J. Huang, J. Bi, X. He, and B. Zhou, “End-to-end structure-aware convolutional networks for knowledge base completion,” in AAAI, vol. 33, 2019, pp. 3060–3067.
45.L. Guo, Z. Sun, and W. Hu, “Learning to exploit long-term relational dependencies in knowledge graphs,” in ICML, 2019, pp. 2505–2514.
46.Q. Wang, P. Huang, H. Wang, S. Dai, W. Jiang, J. Liu, Y. Lyu, Y. Zhu, and H. Wu, “CoKE: Contextualized knowledge graph embedding,” arXiv preprint arXiv:1911.02168, 2019.
47.Y. Wang, R. Gemulla, and H. Li, “On multi-relational link prediction with bilinear models,” in AAAI, 2018, pp. 4227–4234.
48.S. M. Kazemi and D. Poole, “SimplE embedding for link prediction in knowledge graphs,” in NeurIPS, 2018, pp. 4284–4295.
49.M. Nickel, V. Tresp, and H.-P. Kriegel, “A three-way model for collective learning on multi-relational data,” in ICML, vol. 11, 2011, pp. 809–816.
50.——, “Factorizing YAGO: scalable machine learning for linked data,” in WWW, 2012, pp. 271–280.
51.R. Jenatton, N. L. Roux, A. Bordes, and G. R. Obozinski, “A latent factor model for highly multi-relational data,” in NIPS, 2012, pp. 3167–3175.
52.I. Balažević, C. Allen, and T. M. Hospedales, “TuckER: Tensor factorization for knowledge graph completion,” in EMNLP-IJCNLP, 2019, pp. 5185–5194.
53.S. Amin, S. Varanasi, K. A. Dunfield, and G. Neumann, “LowFER: Low-rank bilinear pooling for link prediction,” in ICML, 2020, pp. 1–11.
54.Q. Liu, H. Jiang, A. Evdokimov, Z.-H. Ling, X. Zhu, S. Wei, and Y. Hu, “Probabilistic reasoning via deep learning: Neural association models,” arXiv preprint arXiv:1603.07704, 2016.
55.T. Dettmers, P. Minervini, P. Stenetorp, and S. Riedel, “Convolutional 2d knowledge graph embeddings,” in AAAI, vol. 32, 2018, pp. 1811–1818.
56.I. Balažević, C. Allen, and T. M. Hospedales, “Hypernetwork knowledge graph embeddings,” in ICANN, 2019, pp. 553–565.
57.M. Gardner, P. Talukdar, J. Krishnamurthy, and T. Mitchell, “Incorporating vector space similarity in random walk inference over knowledge bases,” in EMNLP, 2014, pp. 397–406.
58.A. Neelakantan, B. Roth, and A. McCallum, “Compositional vector space models for knowledge base completion,” in ACL-IJCNLP, vol. 1, 2015, pp. 156–166.
59.L. Yao, C. Mao, and Y. Luo, “KG-BERT: BERT for knowledge graph completion,” arXiv preprent arXiv:1909.03193, 2019.
60.M. Schlichtkrull, T. N. Kipf, P. Bloem, R. Van Den Berg, I. Titov, and M. Welling, “Modeling relational data with graph convolutional networks,” in ESWC, 2018, pp. 593–607.
61.T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in ICLR, 2017, pp. 1–14.
62.D. Nathani, J. Chauhan, C. Sharma, and M. Kaul, “Learning attention-based embeddings for relation prediction in knowledge graphs,” in ACL, 2019, pp. 4710–4723.
63.S. Vashishth, S. Sanyal, V. Nitin, and P. Talukdar, “Composition-based multi-relational graph convolutional networks,” in ICLR, 2020, pp. 1–15.
64.Z. Wang, J. Zhang, J. Feng, and Z. Chen, “Knowledge graph and text jointly embedding,” in EMNLP, 2014, pp. 1591–1601.
65.R. Xie, Z. Liu, J. Jia, H. Luan, and M. Sun, “Representation learning of knowledge graphs with entity descriptions,” in AAAI, 2016, pp. 2659–2665.
66.H. Xiao, M. Huang, L. Meng, and X. Zhu, “SSP: semantic space projection for knowledge graph embedding with text descriptions,” in AAAI, 2017, pp. 3104–3110.
67.S. Guo, Q. Wang, B. Wang, L. Wang, and L. Guo, “Semantically smooth knowledge graph embedding,” in ACL-IJCNLP, vol. 1, 2015, pp. 84–94.
68.R. Xie, Z. Liu, and M. Sun, “Representation learning of knowledge graphs with hierarchical types,” in IJCAI, 2016, pp. 2965–2971.
69.Y. Lin, Z. Liu, and M. Sun, “Knowledge representation learning with entities, attributes and relations,” in IJCAI, 2016, pp. 2866–2872.
70.Z. Zhang, F. Zhuang, M. Qu, F. Lin, and Q. He, “Knowledge graph embedding with hierarchical relation structure,” in EMNLP, 2018, pp. 3198–3207.
71.R. Xie, Z. Liu, H. Luan, and M. Sun, “Image-embodied knowledge representation learning,” in IJCAI, 2017, pp. 3140–3146.
72.W. Wu, H. Li, H. Wang, and K. Q. Zhu, “Probase: A probabilistic taxonomy for text understanding,” in SIGMOD, 2012, pp. 481–492.
73.A. Carlson, J. Betteridge, B. Kisiel, B. Settles, E. R. Hruschka, and T. M. Mitchell, “Toward an architecture for never-ending language learning,” in AAAI, 2010, pp. 1306–1313.
74.R. Speer, J. Chin, and C. Havasi, “ConceptNet 5.5: an open multilingual graph of general knowledge,” in Proceedings of AAAI, 2017, pp. 4444–4451.
75.X. Chen, M. Chen, W. Shi, Y. Sun, and C. Zaniolo, “Embedding uncertain knowledge graphs,” in AAAI, vol. 33, 2019, pp. 3363–3370.
76.P. Tabacof and L. Costabello, “Probability calibration for knowledge graph embedding models,” in ICLR, 2019.
77.T. Safavi, D. Koutra, and E. Meij, “Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction,” in Proceedings of EMNLP, 2020, pp. 8308–8321.
78.X. Han, Z. Liu, and M. Sun, “Neural knowledge acquisition via mutual attention between knowledge graph and text,” in AAAI, 2018, pp. 4832–4839.
79.T. Dong, Z. Wang, J. Li, C. Bauckhage, and A. B. Cremers, “Triple classification using regions and fine-grained entity typing,” in AAAI, vol. 33, 2019, pp. 77–85.
80.P. Zhou, W. Shi, J. Tian, Z. Qi, B. Li, H. Hao, and B. Xu, “Attention-based bidirectional long short-term memory networks for relation classification,” in ACL, vol. 2, 2016, pp. 207–212.
81.E. Cao, D. Wang, J. Huang, and W. Hu, “Open knowledge enrichment for long-tail entities,” in The Web Conference, 2020, pp. 384–394.
82.B. Shi and T. Weninger, “ProjE: Embedding projection for knowledge graph completion,” in AAAI, 2017, pp. 1236–1242.
83.S. Guan, X. Jin, Y. Wang, and X. Cheng, “Shared embedding based neural networks for knowledge graph completion,” in CIKM, 2018, pp. 247–256.
84.B. Shi and T. Weninger, “Open-world knowledge graph completion,” in AAAI, 2018, pp. 1957–1964.
85.C. Zhang, Y. Li, N. Du, W. Fan, and P. S. Yu, “On the generative discovery of structured medical knowledge,” in SIGKDD, 2018, pp. 2720–2728.
86.N. Lao and W. W. Cohen, “Relational retrieval using a combination of path-constrained random walks,” Machine learning, vol. 81, no. 1, pp. 53–67, 2010.
87.R. Das, A. Neelakantan, D. Belanger, and A. McCallum, “Chains of reasoning over entities, relations, and text using recurrent neural networks,” in EACL, vol. 1, 2017, pp. 132–141.
88.W. Chen, W. Xiong, X. Yan, and W. Y. Wang, “Variational knowledge graph reasoning,” in NAACL, 2018, pp. 1823–1832.
89.W. Xiong, T. Hoang, and W. Y. Wang, “DeepPath: A reinforcement learning method for knowledge graph reasoning,” in EMNLP, 2017, pp. 564–573.
90.R. Das, S. Dhuliawala, M. Zaheer, L. Vilnis, I. Durugkar, A. Krishnamurthy, A. Smola, and A. McCallum, “Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning,” in ICLR, 2018, pp. 1–18.
91.X. V. Lin, R. Socher, and C. Xiong, “Multi-hop knowledge graph reasoning with reward shaping,” in EMNLP, 2018, pp. 3243–3253.
92.Y. Shen, J. Chen, P.-S. Huang, Y. Guo, and J. Gao, “M-Walk: Learning to walk over graphs using monte carlo tree search,” in NeurIPS, 2018, pp. 6786–6797.
93.C. Fu, T. Chen, M. Qu, W. Jin, and X. Ren, “Collaborative policy learning for open knowledge graph reasoning,” in EMNLP, 2019, pp. 2672–2681.
94.L. A. Galárraga, C. Teflioudi, K. Hose, and F. Suchanek, “AMIE: association rule mining under incomplete evidence in ontological knowledge bases,” in WWW, 2013, pp. 413–422.
95.P. G. Omran, K. Wang, and Z. Wang, “An embedding-based approach to rule learning in knowledge graphs,” IEEE TKDE, pp. 1–12, 2019.
96.S. Guo, Q. Wang, L. Wang, B. Wang, and L. Guo, “Jointly embedding knowledge graphs and logical rules,” in EMNLP, 2016, pp. 192–202.
97.——, “Knowledge graph embedding with iterative guidance from soft rules,” in AAAI, 2018, pp. 4816–4823.
98.W. Zhang, B. Paudel, L. Wang, J. Chen, H. Zhu, W. Zhang, A. Bernstein, and H. Chen, “Iteratively learning embeddings and rules for knowledge graph reasoning,” in WWW, 2019, pp. 2366–2377.
99.T. Rocktäschel and S. Riedel, “End-to-end differentiable proving,” in NIPS, 2017, pp. 3788–3800.
100.F. Yang, Z. Yang, and W. W. Cohen, “Differentiable learning of logical rules for knowledge base reasoning,” in NIPS, 2017, pp. 2319–2328.
101.P.-W. Wang, D. Stepanova, C. Domokos, and J. Z. Kolter, “Differentiable learning of numerical rules in knowledge graphs,” in ICLR, 2020, pp. 1–12.
102.M. Qu and J. Tang, “Probabilistic logic neural networks for reasoning,” in NeurIPS, 2019, pp. 7710–7720.
103.Y. Zhang, X. Chen, Y. Yang, A. Ramamurthy, B. Li, Y. Qi, and L. Song, “Efficient probabilistic logic reasoning with graph neural networks,” in ICLR, 2020, pp. 1–20.
104.W. Xiong, M. Yu, S. Chang, X. Guo, and W. Y. Wang, “One-shot relational learning for knowledge graphs,” in EMNLP, 2018, pp. 1980–1990.
105.X. Lv, Y. Gu, X. Han, L. Hou, J. Li, and Z. Liu, “Adapting meta knowledge graph information for multi-hop reasoning over few-shot relations,” in EMNLP-IJCNLP, 2019, pp. 3374–3379.
106.M. Chen, W. Zhang, W. Zhang, Q. Chen, and H. Chen, “Meta relational learning for few-shot link prediction in knowledge graphs,” in EMNLP-IJCNLP, 2019, pp. 4217–4226.
107.C. Zhang, H. Yao, C. Huang, M. Jiang, Z. Li, and N. V. Chawla, “Few-shot knowledge graph completion,” in AAAI, 2020, pp. 1–8.
108.P. Qin, X. Wang, W. Chen, C. Zhang, W. Xu, and W. Y. Wang, “Generative adversarial zero-shot relational learning for knowledge graphs,” in AAAI, 2020, pp. 1–8.
109.J. Baek, D. B. Lee, and S. J. Hwang, “Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction,” in NeurIPS, 2020.
110.J. P. Chiu and E. Nichols, “Named entity recognition with bidirectional LSTM-CNNs,” Transactions of ACL, vol. 4, pp. 357–370, 2016.
111.G. Lample, M. Ballesteros, S. Subramanian, K. Kawakami, and C. Dyer, “Neural architectures for named entity recognition,” in NAACL, 2016, pp. 260–270.
112.C. Xia, C. Zhang, T. Yang, Y. Li, N. Du, X. Wu, W. Fan, F. Ma, and P. Yu, “Multi-grained named entity recognition,” in ACL, 2019, pp. 1430–1440.
113.A. Hu, Z. Dou, J.-Y. Nie, and J.-R. Wen, “Leveraging multi-token entities in document-level named entity recognition.” in AAAI, 2020, pp. 7961–7968.
114.X. Li, J. Feng, Y. Meng, Q. Han, F. Wu, and J. Li, “A unified MRC framework for named entity recognition,” in ACL, 2020, pp. 5849–5859.
115.Y. Sun, S. Wang, Y. Li, S. Feng, H. Tian, H. Wu, and H. Wang, “ERNIE 2.0: A continual pre-training framework for language understanding,” in AAAI, 2020, pp. 8968–8975.
116.W. Liu, P. Zhou, Z. Zhao, Z. Wang, Q. Ju, H. Deng, and P. Wang, “K-BERT: Enabling language representation with knowledge graph,” in AAAI, 2020, pp. 1–8.
117.X. Ren, W. He, M. Qu, C. R. Voss, H. Ji, and J. Han, “Label noise reduction in entity typing by heterogeneous partial-label embedding,” in SIGKDD, 2016, pp. 1825–1834.
118.Y. Ma, E. Cambria, and S. Gao, “Label embedding for zero-shot fine-grained named entity typing,” in COLING, 2016, pp. 171–180.
119.J. Hao, M. Chen, W. Yu, Y. Sun, and W. Wang, “Universal representation learning of knowledge bases by jointly embedding instances and ontological concepts,” in KDD, 2019, pp. 1709–1719.
120.Y. Zhao, R. Xie, K. Liu, W. Xiaojie et al., “Connecting embeddings for knowledge graph entity typing,” in ACL, 2020, pp. 6419–6428.
121.H. Huang, L. Heck, and H. Ji, “Leveraging deep neural networks and knowledge graphs for entity disambiguation,” arXiv preprint arXiv:1504.07678, 2015.
122.W. Fang, J. Zhang, D. Wang, Z. Chen, and M. Li, “Entity disambiguation by knowledge and text jointly embedding,” in SIGNLL, 2016, pp. 260–269.
123.O.-E. Ganea and T. Hofmann, “Deep joint entity disambiguation with local neural attention,” in EMNLP, 2017, pp. 2619–2629.
124.P. Le and I. Titov, “Improving entity linking by modeling latent relations between mentions,” in ACL, vol. 1, 2018, pp. 1595–1604.
125.M. Chen, Y. Tian, M. Yang, and C. Zaniolo, “Multilingual knowledge graph embeddings for cross-lingual knowledge alignment,” in IJCAI, 2017, pp. 1511–1517.
126.H. Zhu, R. Xie, Z. Liu, and M. Sun, “Iterative entity alignment via joint knowledge embeddings,” in IJCAI, 2017, pp. 4258–4264.
127.Z. Sun, W. Hu, Q. Zhang, and Y. Qu, “Bootstrapping entity alignment with knowledge graph embedding.” in IJCAI, 2018, pp. 4396–4402.
128.Z. Sun, W. Hu, and C. Li, “Cross-lingual entity alignment via joint attribute-preserving embedding,” in ISWC, 2017, pp. 628–644.
129.M. Chen, Y. Tian, K.-W. Chang, S. Skiena, and C. Zaniolo, “Co-training embeddings of knowledge graphs and entity descriptions for cross-lingual entity alignment,” in IJCAI, 2018, pp. 3998–4004.
130.Q. Zhang, Z. Sun, W. Hu, M. Chen, L. Guo, and Y. Qu, “Multi-view knowledge graph embedding for entity alignment,” in IJCAI, 2019, pp. 5429–5435.
131.B. D. Trsedya, J. Qi, and R. Zhang, “Entity alignment between knowledge graphs using attribute embeddings,” in AAAI, vol. 33, 2019, pp. 297–304.
132.Z. Sun, Q. Zhang, W. Hu, C. Wang, M. Chen, F. Akrami, and C. Li, “A benchmarking study of embedding-based entity alignment for knowledge graphs,” in VLDB, 2020.
133.M. Craven, J. Kumlien et al., “Constructing biological knowledge bases by extracting information from text sources,” in ISMB, vol. 1999, 1999, pp. 77–86.
134.M. Mintz, S. Bills, R. Snow, and D. Jurafsky, “Distant supervision for relation extraction without labeled data,” in ACL and IJCNLP of the AFNLP, 2009, pp. 1003–1011.
135.J. Qu, D. Ouyang, W. Hua, Y. Ye, and X. Zhou, “Discovering correlations between sparse features in distant supervision for relation extraction,” in WSDM, 2019, pp. 726–734.
136.D. Zeng, K. Liu, S. Lai, G. Zhou, and J. Zhao, “Relation classification via convolutional deep neural network,” in COLING, 2014, pp. 2335–2344.
137.T. H. Nguyen and R. Grishman, “Relation extraction: Perspective from convolutional neural networks,” in ACL Workshop on Vector Space Modeling for Natural Language Processing, 2015, pp. 39–48.
138.D. Zeng, K. Liu, Y. Chen, and J. Zhao, “Distant supervision for relation extraction via piecewise convolutional neural networks,” in EMNLP, 2015, pp. 1753–1762.
139.X. Jiang, Q. Wang, P. Li, and B. Wang, “Relation extraction with multi-instance multi-label convolutional neural networks,” in COLING, 2016, pp. 1471–1480.
140.H. Ye, W. Chao, Z. Luo, and Z. Li, “Jointly extracting relations with class ties via effective deep ranking,” in ACL, vol. 1, 2017, pp. 1810–1820.
141.W. Zeng, Y. Lin, Z. Liu, and M. Sun, “Incorporating relation paths in neural relation extraction,” in EMNLP, 2017, pp. 1768–1777.
142.Y. Xu, L. Mou, G. Li, Y. Chen, H. Peng, and Z. Jin, “Classifying relations via long short term memory networks along shortest dependency paths,” in EMNLP, 2015, pp. 1785–1794.
143.M. Miwa and M. Bansal, “End-to-end relation extraction using lstms on sequences and tree structures,” in ACL, vol. 1, 2016, pp. 1105–1116.
144.R. Cai, X. Zhang, and H. Wang, “Bidirectional recurrent convolutional neural network for relation classification,” in ACL, vol. 1, 2016, pp. 756–765.
145.Y. Shen and X. Huang, “Attention-based convolutional neural network for semantic relation extraction,” in COLING, 2016, pp. 2526–2536.
146.Y. Lin, S. Shen, Z. Liu, H. Luan, and M. Sun, “Neural relation extraction with selective attention over instances,” in ACL, vol. 1, 2016, pp. 2124–2133.
147.G. Ji, K. Liu, S. He, and J. Zhao, “Distant supervision for relation extraction with sentence-level attention and entity descriptions,” in AAAI, 2017, pp. 3060–3066.
148.X. Han, P. Yu, Z. Liu, M. Sun, and P. Li, “Hierarchical relation extraction with coarse-to-fine grained attention,” in EMNLP, 2018, pp. 2236–2245.
149.L. B. Soares, N. FitzGerald, J. Ling, and T. Kwiatkowski, “Matching the blanks: Distributional similarity for relation learning,” in ACL, 2019, pp. 2895–2905.
150.Y. Zhang, P. Qi, and C. D. Manning, “Graph convolution over pruned dependency trees improves relation extraction,” in EMNLP, 2018, pp. 2205–2215.
151.Z. Guo, Y. Zhang, and W. Lu, “Attention guided graph convolutional networks for relation extraction,” in ACL, 2019, pp. 241–251.
152.N. Zhang, S. Deng, Z. Sun, G. Wang, X. Chen, W. Zhang, and H. Chen, “Long-tail relation extraction via knowledge graph embeddings and graph convolution networks,” in NAACL, 2019, pp. 3016–3025.
153.Y. Wu, D. Bamman, and S. Russell, “Adversarial training for relation extraction,” in EMNLP, 2017, pp. 1778–1783.
154.P. Qin, X. Weiran, and W. Y. Wang, “DSGAN: Generative adversarial training for distant supervision relation extraction,” in ACL, vol. 1, 2018, pp. 496–505.
155.P. Qin, W. Xu, and W. Y. Wang, “Robust distant supervision relation extraction via deep reinforcement learning,” in ACL, vol. 1, 2018, pp. 2137–2147.
156.X. Zeng, S. He, K. Liu, and J. Zhao, “Large scaled relation extraction with reinforcement learning,” in AAAI, 2018, pp. 5658–5665.
157.J. Feng, M. Huang, L. Zhao, Y. Yang, and X. Zhu, “Reinforcement learning for relation classification from noisy data,” in AAAI, 2018, pp. 5779–5786.
158.R. Takanobu, T. Zhang, J. Liu, and M. Huang, “A hierarchical framework for relation extraction with reinforcement learning,” in AAAI, vol. 33, 2019, pp. 7072–7079.
159.Y. Huang and W. Y. Wang, “Deep residual learning for weakly-supervised relation extraction,” in EMNLP, 2017, pp. 1803–1807.
160.T. Liu, X. Zhang, W. Zhou, and W. Jia, “Neural relation extraction via inner-sentence noise reduction and transfer learning,” in EMNLP, 2018, pp. 2195–2204.
161.K. Lei, D. Chen, Y. Li, N. Du, M. Yang, W. Fan, and Y. Shen, “Cooperative denoising for distantly supervised relation extraction,” in COLING, 2018, pp. 426–436.
162.H. Jiang, L. Cui, Z. Xu, D. Yang, J. Chen, C. Li, J. Liu, J. Liang, C. Wang, Y. Xiao, and W. Wang, “Relation extraction using supervision from topic knowledge of relation labels,” in IJCAI, 2019, pp. 5024–5030.
163.H. Shahbazi, X. Z. Fern, R. Ghaeini, and P. Tadepalli, “Relation extraction with explanation,” in ACL, 2020, pp. 6488–6494.
164.T. Gao, X. Han, Z. Liu, and M. Sun, “Hybrid attention-based prototypical networks for noisy few-shot relation classification,” in AAAI, vol. 33, 2019, pp. 6407–6414.
165.M. Qu, T. Gao, L.-P. A. Xhonneux, and J. Tang, “Few-shot relation extraction via bayesian meta-learning on relation graphs,” in ICML, 2020, pp. 1–10.
166.M. Miwa and Y. Sasaki, “Modeling joint entity and relation extraction with table representation,” in EMNLP, 2014, pp. 1858–1869.
167.A. Katiyar and C. Cardie, “Going out on a limb: Joint extraction of entity mentions and relations without dependency trees,” in ACL, 2017, pp. 917–928.
168.S. Zheng, F. Wang, H. Bao, Y. Hao, P. Zhou, and B. Xu, “Joint extraction of entities and relations based on a novel tagging scheme,” in ACL, 2017, pp. 1227–1236.
169.X. Li, F. Yin, Z. Sun, X. Li, A. Yuan, D. Chai, M. Zhou, and J. Li, “Entity-relation extraction as multi-turn question answering,” in ACL, 2019, pp. 1340–1350.
170.D. Dai, X. Xiao, Y. Lyu, S. Dou, Q. She, and H. Wang, “Joint extraction of entities and overlapping relations using position-attentive sequence labeling,” in AAAI, vol. 33, 2019, pp. 6300–6308.
171.Z. Wei, J. Su, Y. Wang, Y. Tian, and Y. Chang, “A novel cascade binary tagging framework for relational triple extraction,” in ACL, 2020, pp. 1476–1488.
172.Y. Wang, B. Yu, Y. Zhang, T. Liu, H. Zhu, and L. Sun, “Tplinker: Single-stage joint extraction of entities and relations through token pair linking,” in COLING, 2020, pp. 1572–1582.
173.Z. Zhong and D. Chen, “A frustratingly easy approach for joint entity and relation extraction,” arXiv preprint arXiv:2010.12812, 2020.
174.D. Xu, C. Ruan, E. Korpeoglu, S. Kumar, and K. Achan, “Inductive representation learning on temporal graphs,” in ICLR, 2020, pp. 1–19.
175.J. Leblay and M. W. Chekol, “Deriving validity time in knowledge graph,” in WWW, 2018, pp. 1771–1776.
176.Y. Ma, V. Tresp, and E. A. Daxberger, “Embedding models for episodic knowledge graphs,” Journal of Web Semantics, vol. 59, p. 100490, 2019.
177.S. S. Dasgupta, S. N. Ray, and P. Talukdar, “Hyte: Hyperplane-based temporally aware knowledge graph embedding,” in EMNLP, 2018, pp. 2001–2011.
178.A. García-Durán, S. Dumančić, and M. Niepert, “Learning sequence encoders for temporal knowledge graph completion,” in EMNLP, 2018, pp. 4816–4821.
179.Y. Liu, W. Hua, K. Xin, and X. Zhou, “Context-aware temporal knowledge graph embedding,” in WISE, 2019, pp. 583–598.
180.T. Lacroix, G. Obozinski, and N. Usunier, “Tensor decompositions for temporal knowledge base completion,” in ICLR, 2020, pp. 1–12.
181.D. T. Wijaya, N. Nakashole, and T. M. Mitchell, “CTPs: Contextual temporal profiles for time scoping facts using state change detection,” in EMNLP, 2014, pp. 1930–1936.
182.R. Goel, S. M. Kazemi, M. Brubaker, and P. Poupart, “Diachronic embedding for temporal knowledge graph completion,” in AAAI, 2020, pp. 3988–3995.
183.R. Trivedi, H. Dai, Y. Wang, and L. Song, “Know-evolve: Deep temporal reasoning for dynamic knowledge graphs,” in ICML, 2017, pp. 3462–3471.
184.W. Jin, C. Zhang, P. Szekely, and X. Ren, “Recurrent event network for reasoning over temporal knowledge graphs,” in ICLR RLGM Workshop, 2019.
185.T. Jiang, T. Liu, T. Ge, L. Sha, B. Chang, S. Li, and Z. Sui, “Towards time-aware knowledge graph completion,” in COLING, 2016, pp. 1715–1724.
186.T. Jiang, T. Liu, T. Ge, L. Sha, S. Li, B. Chang, and Z. Sui, “Encoding temporal information for time-aware link prediction,” in EMNLP, 2016, pp. 2350–2354.
187.M. W. Chekol, G. Pirrò, J. Schoenfisch, and H. Stuckenschmidt, “Marrying uncertainty and time in knowledge graphs,” in AAAI, 2017, pp. 88–94.
188.R. Logan, N. F. Liu, M. E. Peters, M. Gardner, and S. Singh, “Barack’s wife hillary: Using knowledge graphs for fact-aware language modeling,” in ACL, 2019, pp. 5962–5971.
189.Z. Zhang, X. Han, Z. Liu, X. Jiang, M. Sun, and Q. Liu, “ERNIE: Enhanced language representation with informative entities,” in ACL, 2019, pp. 1441–1451.
190.Y. Sun, S. Wang, Y. Li, S. Feng, X. Chen, H. Zhang, X. Tian, D. Zhu, H. Tian, and H. Wu, “ERNIE: Enhanced representation through knowledge integration,” arXiv preprint arXiv:1904.09223, 2019.
191.X. Wang, T. Gao, Z. Zhu, Z. Liu, J. Li, and J. Tang, “KEPLER: A unified model for knowledge embedding and pre-trained language representation,” TACL, 2020.
192.T. Shen, Y. Mao, P. He, G. Long, A. Trischler, and W. Chen, “Exploiting structured knowledge in text via graph-guided representation learning,” in EMNLP, 2020.
193.T. Sun, Y. Shao, X. Qiu, Q. Guo, Y. Hu, X.-J. Huang, and Z. Zhang, “CoLAKE: Contextualized Language and Knowledge Embedding,” in COLING, 2020, pp. 3660–3670.
194.B. He, D. Zhou, J. Xiao, Q. Liu, N. J. Yuan, T. Xu et al., “BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models,” in Findings of EMNLP, 2020, p. 2281–2290.
195.F. Petroni, T. Rocktäschel, S. Riedel, P. Lewis, A. Bakhtin, Y. Wu, and A. Miller, “Language models as knowledge bases?” in EMNLP-IJCNLP, 2019, pp. 2463–2473.
196.Z. Dai, L. Li, and W. Xu, “CFO: Conditional focused neural question answering with large-scale knowledge bases,” in ACL, vol. 1, 2016, pp. 800–810.
197.Y. Chen, L. Wu, and M. J. Zaki, “Bidirectional attentive memory networks for question answering over knowledge bases,” in NAACL, 2019, pp. 2913–2923.
198.S. Mohammed, P. Shi, and J. Lin, “Strong baselines for simple question answering over knowledge graphs with and without neural networks,” in NAACL, 2018, pp. 291–296.
199.L. Bauer, Y. Wang, and M. Bansal, “Commonsense for generative multi-hop question answering tasks,” in EMNLP, 2018, pp. 4220–4230.
200.Y. Zhang, H. Dai, Z. Kozareva, A. J. Smola, and L. Song, “Variational reasoning for question answering with knowledge graph,” in AAAI, 2018, pp. 6069–6076.
201.B. Y. Lin, X. Chen, J. Chen, and X. Ren, “KagNet: Knowledge-aware graph networks for commonsense reasoning,” in EMNLP-IJCNLP, 2019, pp. 2829–2839.
202.M. Ding, C. Zhou, Q. Chen, H. Yang, and J. Tang, “Cognitive graph for multi-hop reading comprehension at scale,” in ACL, 2019, pp. 2694–2703.
203.F. Zhang, N. J. Yuan, D. Lian, X. Xie, and W.-Y. Ma, “Collaborative knowledge base embedding for recommender systems,” in SIGKDD, 2016, pp. 353–362.
204.H. Wang, F. Zhang, X. Xie, and M. Guo, “DKN: Deep knowledge-aware network for news recommendation,” in WWW, 2018, pp. 1835–1844.
205.H. Wang, F. Zhang, M. Zhao, W. Li, X. Xie, and M. Guo, “Multi-task feature learning for knowledge graph enhanced recommendation,” in WWW, 2019, pp. 2000–2010.
206.X. Wang, D. Wang, C. Xu, X. He, Y. Cao, and T.-S. Chua, “Explainable reasoning over knowledge graphs for recommendation,” in AAAI, vol. 33, 2019, pp. 5329–5336.
207.Y. Xian, Z. Fu, S. Muthukrishnan, G. de Melo, and Y. Zhang, “Reinforcement knowledge graph reasoning for explainable recommendation,” in SIGIR, 2019.
208.X. Wang, X. He, Y. Cao, M. Liu, and T.-S. Chua, “KGAT: Knowledge graph attention network for recommendation,” in SIGKDD, 2019, pp. 950–958.
209.A. Sharma, P. Talukdar et al., “Towards understanding the geometry of knowledge graph embeddings,” in ACL, 2018, pp. 122–131.
210.P. W. Battaglia, J. B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner et al., “Relational inductive biases, deep learning, and graph networks,” arXiv preprint arXiv:1806.01261, 2018.
211.M. Fan, Q. Zhou, E. Chang, and T. F. Zheng, “Transition-based knowledge graph embedding with relational mapping properties,” in PACLIC, 2014, pp. 328–337.
212.G. Ji, K. Liu, S. He, and J. Zhao, “Knowledge graph completion with adaptive sparse transfer matrix,” in AAAI, 2016, pp. 985–991.
213.A. García-Durán, A. Bordes, and N. Usunier, “Effective blending of two and three-way interactions for modeling multi-relational data,” in ECML. Springer, 2014, pp. 434–449.
214.R. Reiter, “Deductive question-answering on relational data bases,” in Logic and data bases. Springer, 1978, pp. 149–177.
215.L. Cai and W. Y. Wang, “KBGAN: Adversarial learning for knowledge graph embeddings,” in NAACL, 2018, pp. 1470–1480.
216.J. Wang, Z. Wang, D. Zhang, and J. Yan, “Combining knowledge with deep convolutional neural networks for short text classification.” in IJCAI, 2017, pp. 2915–2921.
217.H. Peng, J. Li, Q. Gong, Y. Song, Y. Ning, K. Lai, and P. S. Yu, “Fine-grained event categorization with heterogeneous graph convolutional networks,” in IJCAI, 2019, pp. 3238–3245.
218.M. Gaur, A. Alambo, J. P. Sain, U. Kursuncu, K. Thirunarayan, R. Kavuluru, A. Sheth, R. S. Welton, and J. Pathak, “Knowledge-aware assessment of severity of suicide risk for early intervention,” in WWW, 2019, pp. 514–525.
219.E. Cambria, S. Poria, D. Hazarika, and K. Kwok, “SenticNet 5: Discovering conceptual primitives for sentiment analysis by means of context embeddings,” in AAAI, 2018, pp. 1795–1802.
220.Y. Ma, H. Peng, and E. Cambria, “Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive lstm,” in AAAI, 2018, pp. 5876–5883.
221.Z. Liu, Z.-Y. Niu, H. Wu, and H. Wang, “Knowledge aware conversation generation with explainable reasoning over augmented graphs,” in EMNLP, 2019, pp. 1782–1792.
222.S. Moon, P. Shah, A. Kumar, and R. Subba, “OpenDialKG: Explainable conversational reasoning with attention-based walks over knowledge graphs,” in ACL, 2019, pp. 845–854.
223.D. Guo, D. Tang, N. Duan, M. Zhou, and J. Yin, “Dialog-to-Action: Conversational question answering over a large-scale knowledge base,” in NeurIPS, 2018, pp. 2942–2951.
224.R. T. Sousa, S. Silva, and C. Pesquita, “Evolving knowledge graph similarity for supervised learning in complex biomedical domains,” BMC Bioinformatics, vol. 21, no. 1, p. 6, 2020.
225.S. K. Mohamed, V. Nováček, and A. Nounu, “Discovering protein drug targets using knowledge graph embeddings,” Bioinformatics, vol. 36, no. 2, pp. 603–610, 2020.
226.X. Lin, Z. Quan, Z.-J. Wang, T. Ma, and X. Zeng, “KGNN: Knowledge graph neural network for drug-drug interaction prediction.” IJCAI, 2020.
227.B. Hao, H. Zhu, and I. Paschalidis, “Enhancing Clinical BERT Embedding using a Biomedical Knowledge Base,” in Proceedings of COLING, 2020, pp. 657–661.
228.C. Y. Li, X. Liang, Z. Hu, and E. P. Xing, “Knowledge-driven encode, retrieve, paraphrase for medical image report generation,” arXiv preprint arXiv:1903.10122, 2019.
229.C. Xiong, R. Power, and J. Callan, “Explicit semantic ranking for academic search via knowledge graph embedding,” in WWW, 2017, pp. 1271–1279.
230.X. Wang, Y. Ye, and A. Gupta, “Zero-shot recognition via semantic embeddings and knowledge graphs,” in CVPR, 2018, pp. 6857–6866.
231.L. Liu, T. Zhou, G. Long, J. Jiang, and C. Zhang, “Attribute propagation network for graph zero-shot learning,” in AAAI, 2020, pp. 4868–4875.
232.R. Koncel-Kedziorski, D. Bekal, Y. Luan, M. Lapata, and H. Hajishirzi, “Text generation from knowledge graphs with graph transformers,” in NAACL, 2019, pp. 2284–2293.
233.D. Seyler, M. Yahya, and K. Berberich, “Knowledge questions from knowledge graphs,” in SIGIR, 2017, pp. 11–18.
234.G. A. Miller, “WordNet: a lexical database for english,” Communications of the ACM, vol. 38, no. 11, pp. 39–41, 1995.
235.C. Matuszek, M. Witbrock, J. Cabral, and J. DeOliveira, “An introduction to the syntax and content of cyc,” in AAAI Spring Symposium on Formalizing and Compiling Background Knowledge and Its Applications to Knowledge Representation and Question Answering, 2006, pp. 1–6.
236.S. Auer, C. Bizer, G. Kobilarov, J. Lehmann, R. Cyganiak, and Z. Ives, “Dbpedia: A nucleus for a web of open data,” in The semantic web, 2007, pp. 722–735.
237.F. M. Suchanek, G. Kasneci, and G. Weikum, “Yago: a core of semantic knowledge,” in WWW, 2007, pp. 697–706.
238.K. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor, “Freebase: a collaboratively created graph database for structuring human knowledge,” in SIGMOD, 2008, pp. 1247–1250.
239.D. Vrandečić and M. Krötzsch, “Wikidata: a free collaborative knowledge base,” Communications of the ACM, vol. 57, no. 10, pp. 78–85, 2014.
240.A. T. McCray, “An upper-level ontology for the biomedical domain,” International Journal of Genomics, vol. 4, no. 1, pp. 80–84, 2003.
241.I. H. Moal and J. Fernández-Recio, “SKEMPI: a Structural Kinetic and Energetic database of Mutant Protein Interactions and its use in empirical models,” Bioinformatics, vol. 28, no. 20, pp. 2600–2607, 2012.
242.H. M. Berman, J. Westbrook, Z. Feng, G. Gilliland, T. N. Bhat, H. Weissig, I. N. Shindyalov, and P. E. Bourne, “The protein data bank,” Nucleic acids research, vol. 28, no. 1, pp. 235–242, 2000.
243.D. S. Wishart, C. Knox, A. C. Guo, S. Shrivastava, M. Hassanali, P. Stothard, Z. Chang, and J. Woolsey, “DrugBank: a comprehensive resource for in silico drug discovery and exploration,” Nucleic acids research, vol. 34, no. suppl_1, pp. D668–D672, 2006.
244.D. S. Wishart, C. Knox, A. C. Guo, D. Cheng, S. Shrivastava, D. Tzur, B. Gautam, and M. Hassanali, “DrugBank: a knowledgebase for drugs, drug actions and drug targets,” Nucleic acids research, vol. 36, no. suppl_1, pp. D901–D906, 2008.
245.S. Riedel, L. Yao, and A. McCallum, “Modeling relations and their mentions without labeled text,” in ECML, 2010, pp. 148–163.
246.E. Cambria, Y. Song, H. Wang, and N. Howard, “Semantic multidimensional scaling for open-domain sentiment analysis,” IEEE Intelligent Systems, vol. 29, no. 2, pp. 44–51, 2012.
247.X. Han, H. Zhu, P. Yu, Z. Wang, Y. Yao, Z. Liu, and M. Sun, “Fewrel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation,” in EMNLP, 2018, pp. 4803–4809.
248.K. Toutanova and D. Chen, “Observed versus latent features for knowledge base and text inference,” in ACL Workshop on CVSC, 2015, pp. 57–66.
249.S. Ahn, H. Choi, T. Pärnamaa, and Y. Bengio, “A neural knowledge language model,” arXiv preprint arXiv:1608.00318, 2016.
250.A. Bordes, N. Usunier, S. Chopra, and J. Weston, “Large-scale simple question answering with memory networks,” arXiv preprint arXiv:1506.02075, 2015.
251.P. Trivedi, G. Maheshwari, M. Dubey, and J. Lehmann, “LC-QuAD: A corpus for complex question answering over knowledge graphs,” in ISWC, 2017, pp. 210–218.
252.L. Costabello, S. Pai, C. L. Van, R. McGrath, and N. McCarthy, “AmpliGraph: a Library for Representation Learning on Knowledge Graphs,” 2019.
253.X. Han, S. Cao, L. Xin, Y. Lin, Z. Liu, M. Sun, and J. Li, “OpenKE: An open toolkit for knowledge embedding,” in EMNLP, 2018, pp. 139–144.
254.X. Han, T. Gao, Y. Yao, D. Ye, Z. Liu, and M. Sun, “OpenNRE: An open and extensible toolkit for neural relation extraction,” in EMNLP-IJCNLP, 2019, pp. 169–174.

Citation

MLA

Ji, S., et al. “A Survey on Knowledge Graphs: Representation, Acquisition, and Applications”. IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 2, 2022, pp. 494–514, https://doi.org/10.1109/TNNLS.2021.3070843.

APA

Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2022). A Survey on Knowledge Graphs: Representation, Acquisition, and Applications. IEEE Transactions on Neural Networks and Learning Systems, 33(2), 494–514. https://doi.org/10.1109/TNNLS.2021.3070843

Chicago

Ji, S., S. Pan, E. Cambria, P. Marttinen, and P. S. Yu. 2022. “A Survey on Knowledge Graphs: Representation, Acquisition, and Applications”. IEEE Transactions on Neural Networks and Learning Systems 33 (2): 494–514. https://doi.org/10.1109/TNNLS.2021.3070843.

Harvard

Ji, S. et al. (2022) “A Survey on Knowledge Graphs: Representation, Acquisition, and Applications”, IEEE Transactions on Neural Networks and Learning Systems, 33(2), pp. 494–514. Available at: https://doi.org/10.1109/TNNLS.2021.3070843.

Vancouver

1. Ji S, Pan S, Cambria E, Marttinen P, Yu PS (2022) A Survey on Knowledge Graphs: Representation, Acquisition, and Applications. IEEE Transactions on Neural Networks and Learning Systems 33:494–514

BibTeX

@article{Ji_2022, title={A Survey on Knowledge Graphs: Representation, Acquisition, and Applications}, volume={33}, ISSN={2162-2388}, url={http://dx.doi.org/10.1109/TNNLS.2021.3070843}, DOI={10.1109/tnnls.2021.3070843}, number={2}, journal={IEEE Transactions on Neural Networks and Learning Systems}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Ji, Shaoxiong and Pan, Shirui and Cambria, Erik and Marttinen, Pekka and Yu, Philip S.}, year={2022}, month=Feb, pages={494–514} }

Metadata:Crossref

Source Code

This paper has an official code repository available. Click below to access the source code.

View Repository

Access the Paper

This paper is available from its original source. Click below to access the PDF.

Open PDF

A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

Abstract

Topics

Keywords

Table of Contents

Knowls

Knowl 1 — Taxonomy and Conceptual Workflow of Knowledge Representation Learning

Knowl 2 — Mathematical Formulations of Knowledge Graph Scoring Functions

Knowl 3 — Non-Euclidean and Geometric Representation Spaces for Knowledge Graphs

Knowl 4 — Training Assumptions, Loss Objectives, and Negative Sampling Strategies

Knowl 5 — Multi-Hop Relational Path Finding via Reinforcement Learning

Knowl 6 — Neuro-Symbolic and Rule-Based Reasoning for Knowledge Graph Completion

Knowl 7 — Meta Relational and Few-Shot Learning for Knowledge Graph Completion

Knowl 8 — Neural Paradigms for Distantly Supervised Relation Extraction

Knowl 9 — Entity Discovery Taxonomy: Recognition, Typing, Disambiguation, and Alignment

Knowl 10 — Temporal Knowledge Graph Representation and Dynamics

Knowl 11 — Knowledge-Aware Downstream Applications: Language Pretraining, QA, and Recommendations

References

Citation

BibTeX

Source Code

Access the Paper