HiPerformer: Hierarchically Permutation-Equivariant Transformer for Time Series Forecasting

TL;DR

This paper introduces HiPerformer, a hierarchical permutation-equivariant transformer model that captures group-structured relationships in multivariate time series, improving forecasting accuracy.

Contribution

The paper proposes a novel hierarchical permutation-equivariance concept and a transformer model that leverages group structures for better time series forecasting.

Findings

Outperforms existing state-of-the-art methods on real-world data

Effectively captures intra-group and inter-group relationships

Enhances forecasting accuracy through hierarchical structure modeling

Abstract

It is imperative to discern the relationships between multiple time series for accurate forecasting. In particular, for stock prices, components are often divided into groups with the same characteristics, and a model that extracts relationships consistent with this group structure should be effective. Thus, we propose the concept of hierarchical permutation-equivariance, focusing on index swapping of components within and among groups, to design a model that considers this group structure. When the prediction model has hierarchical permutation-equivariance, the prediction is consistent with the group relationships of the components. Therefore, we propose a hierarchically permutation-equivariant model that considers both the relationship among components in the same group and the relationship among groups. The experiments conducted on real-world data demonstrate that the proposed method outperforms existing state-of-the-art methods.