HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis

TL;DR

A novel hypergraph-based time series Transformer backbone network, termed HGTS-Former, to address the multivariate coupling in time series data and presents EAST-ELM640, a large-scale time series dataset for Edge-Localized Mode (ELM) recognition in nuclear fusion, on which it achieves state-of-the-art performance.

Abstract

Multivariate time series analysis has long been one of the key research topics in the field of artificial intelligence. However, analyzing complex time series data remains a challenging and unresolved problem due to its high dimensionality, dynamic nature, and complex interactions among variables. Inspired by the strong structural modeling capability of hypergraphs, this paper proposes a novel hypergraph-based time series Transformer backbone network, termed HGTS-Former, to address the multivariate coupling in time series data. Specifically, given the multivariate time series signal, we first normalize and embed each patch into tokens. Then, we adopt the multi-head self-attention to enhance the temporal representation of each patch. The hierarchical hypergraphs are constructed to aggregate the temporal patterns within each channel and fine-grained relations between different variables. After that, we convert the hyperedge into node features through the EdgeToNode module and adopt the feed-forward network to further enhance the output features. Extensive experiments on multiple representative time series analysis tasks and public datasets fully validated the effectiveness of our proposed HGTS-Former. Moreover, we present EAST-ELM640, a large-scale time series dataset for Edge-Localized Mode (ELM) recognition in nuclear fusion, on which we achieve state-of-the-art performance. The source code will be released on https://github.com/Event-AHU/Time_Series_Analysis

Figures (8)

• Figure 1: Comparison between existing time series models and our newly proposed Hierarchical Hypergraph Transformer.
• Figure 2: An overview of our proposed HyperGraph Time Series Transformer. We use the Intra-/Inter-HGA module to construct the hierarchical hypergraph in (b) and perform fine-grained aggregation within variables and coarse-grained aggregation between variables.
• Figure 3: Imputation result of our proposed model on the ETTh1 and ETTh2 datasets.
• Figure 4: An illustration of representative samples in the EAST-ELM640 datasets.
• Figure 5: Comparison of the predicted results between ours and Timer-XL on samples from the ETTh1 and ETTh2 datasets.