Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

multi-stage graph embedding

Multi-stage graph embedding is a graph representation learning process that converts the topological structure and properties of a graph into low-dimensional vector spaces through a sequence of distinct computational phases. Instead of encoding graph elements in a single step, this approach iteratively extracts, aggregates, and refines information across multiple stages, such as hierarchical structural levels, subgraphs, or progressive neighborhood aggregation layers. This staged processing allows the model to comprehensively capture fine-grained local node interactions alongside broad topological motifs and global structural dependencies. The resulting embeddings preserve rich structural context, making them useful for downstream optimization, classification, and decision-making tasks across complex graph-structured data.

1 item

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Sixing Yu, Arya Mazaheri, Ali Jannesari

OrganizationsIowa State UniversityTechnische Universität Darmstadt

Why you should read this

Proposes a multi-stage graph embedding framework that captures hierarchical neural network topologies to automatically learn optimal, FLOP-constrained pruning policies via reinforcement learning across diverse architectures.

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters’ local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach with state-of-the-art model compression methods. We evaluated our method on various models from typical to mobile-friendly networks, such as ResNet family, VGG-16, MobileNet-v1/v2, and ShuffleNet. Results show that our method can achieve higher compression ratios with a minimal fine-tuning cost yet yields outstanding and competitive performance. The code is open-sourced at https://github.com/yusx-swapp/GNN-RL-Model-Compression.

Added

2026-10-03