HiPerformer: Hierarchically Permutation-Equivariant Transformer for Time Series Forecasting
This addresses forecasting accuracy for domains like stock prices where components are grouped, but it is incremental as it builds on existing permutation-equivariant methods.
The paper tackled the problem of forecasting multiple time series by proposing a model that respects hierarchical group structures, achieving state-of-the-art performance on real-world data.
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.