Dynamic Relation Discovery and Utilization in Multi-Entity Time Series Forecasting

TL;DR

This paper introduces A2GNN, a novel neural network that automatically discovers and utilizes implicit and explicit relations among multiple entities in time series forecasting, significantly improving accuracy across various domains.

Contribution

The paper proposes a new attentional multi-graph neural network with automatic graph learning to dynamically discover and leverage entity relations in multi-entity time series forecasting.

Findings

A2GNN outperforms several state-of-the-art methods on five real-world datasets.

The Gumbel-softmax auto graph learner effectively captures implicit relations.

Dynamic relation utilization improves forecasting accuracy across domains.

Abstract

Time series forecasting plays a key role in a variety of domains. In a lot of real-world scenarios, there exist multiple forecasting entities (e.g. power station in the solar system, stations in the traffic system). A straightforward forecasting solution is to mine the temporal dependency for each individual entity through 1d-CNN, RNN, transformer, etc. This approach overlooks the relations between these entities and, in consequence, loses the opportunity to improve performance using spatial-temporal relation. However, in many real-world scenarios, beside explicit relation, there could exist crucial yet implicit relation between entities. How to discover the useful implicit relation between entities and effectively utilize the relations for each entity under various circumstances is crucial. In order to mine the implicit relation between entities as much as possible and dynamically utilize the relation to improve the forecasting performance, we propose an attentional multi-graph neural network with automatic graph learning (A2GNN) in this work. Particularly, a Gumbel-softmax based auto graph learner is designed to automatically capture the implicit relation among forecasting entities. We further propose an attentional relation learner that enables every entity to dynamically pay attention to its preferred relations. Extensive experiments are conducted on five real-world datasets from three different domains. The results demonstrate the effectiveness of A2GNN beyond several state-of-the-art methods.