HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting

2025-05-23

AI Summary

Irregular multivariate time series (IMTS) forecasting faces challenges including non-uniform inter-observation intervals, misaligned observations across variables, and limited dependency modeling due to reliance on interpolation, padding, or bipartite graph structures. Method: This paper proposes the first end-to-end hypergraph-based forecasting framework for IMTS. It directly models raw irregular observations as hypergraph nodes and introduces dynamic hyperedges operating jointly along temporal and variable dimensions, enabling irregularity-aware message passing across both variables and time points. Crucially, hyperedge construction is differentiable and requires neither interpolation nor padding, fully preserving original sampling characteristics. Contribution/Results: Evaluated on multiple IMTS benchmarks, the method significantly outperforms state-of-the-art approaches—achieving higher prediction accuracy while reducing computational overhead.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Irregular multivariate time series (IMTS) are characterized by irregular time intervals within variables and unaligned observations across variables, posing challenges in learning temporal and variable dependencies. Many existing IMTS models either require padded samples to learn separately from temporal and variable dimensions, or represent original samples via bipartite graphs or sets. However, the former approaches often need to handle extra padding values affecting efficiency and disrupting original sampling patterns, while the latter ones have limitations in capturing dependencies among unaligned observations. To represent and learn both dependencies from original observations in a unified form, we propose HyperIMTS, a Hypergraph neural network for Irregular Multivariate Time Series forecasting. Observed values are converted as nodes in the hypergraph, interconnected by temporal and variable hyperedges to enable message passing among all observations. Through irregularity-aware message passing, HyperIMTS captures variable dependencies in a time-adaptive way to achieve accurate forecasting. Experiments demonstrate HyperIMTS's competitive performance among state-of-the-art models in IMTS forecasting with low computational cost.

Problem

• Handling irregular time intervals in multivariate time series
• Capturing dependencies among unaligned observations effectively
• Achieving accurate forecasting with low computational cost

Innovation

• Hypergraph neural network for IMTS forecasting
• Temporal and variable hyperedges connect nodes
• Irregularity-aware message passing captures dependencies