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

keyword

intra-series temporal patterns

Intra-series temporal patterns refer to the sequential trends, cycles, and chronological dependencies that occur within a single, individual time series over time. These dynamics capture how historical values of a particular variable influence its own subsequent states across different time scales, encompassing both short-range fluctuations between adjacent time steps and long-range seasonal or recurring behaviors. Unlike inter-series correlations, which represent the interactions and dependencies between multiple distinct time series, intra-series patterns focus exclusively on the internal evolution of an isolated sequence. Modeling these internal temporal structures is essential in time series analysis and forecasting to comprehend the specific evolutionary trajectory and future behavior of an individual data stream.

1 item

CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting

CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting

Hui He, Qi Zhang, Simeng Bai, Kun Yi, Zhendong Niu

OrganizationsBeijing Institute of TechnologyDeepBlue Academy of SciencesUniversity of PittsburghUniversity of Technology Sydney

Why you should read this

Proposes an end-to-end framework that constructs hierarchical tree structures to capture grouped correlations across variables and uses a cross-attention mechanism to jointly model dynamic inter-series and intra-series temporal dependencies for multivariate time series forecasting.

Modeling complex hierarchical and grouped feature interaction in the multivariate time series data is indispensable to comprehending the data dynamics and predicting the future condition. The implicit feature interaction and high-dimensional data make multivariate forecasting very challenging. Many existing works did not put more emphasis on exploring explicit correlation among multiple time-series data, and complicated models are designed to capture long- and short-range patterns with the aid of attention mechanisms. In this work, we think that a pre-defined graph or a general learning method is difficult due to its irregular structure. Hence, we present CATN, an end-to-end model of Cross Attentive Tree-aware Network to jointly capture the inter-series correlation and intra-series temporal patterns. We first construct a tree structure to learn hierarchical and grouped correlation and design an embedding approach that can pass a dynamic message to generalize implicit but interpretable cross features among multiple time series. Next in the temporal aspect, we propose a multi-level dependency learning mechanism including global&local learning and cross attention mechanism, which can combine long-range dependencies, short-range dependencies as well as cross dependencies at different time steps. The extensive experiments on different datasets from real-world show the effectiveness and robustness of the method we proposed when compared with existing state-of-the-art methods.

Added

2026-09-26