Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting

TL;DR

This paper introduces RGSL, a novel model that combines explicit prior and implicit graph structures to improve multivariate time-series forecasting, demonstrating superior performance on real datasets.

Contribution

The paper proposes a new regularized graph structure learning method that fuses explicit and implicit graph information for enhanced forecasting accuracy.

Findings

Outperforms existing graph forecasting algorithms

Learns meaningful and accurate graph structures

Effective on multiple real-world datasets

Abstract

Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal correlation simultaneously. However, most existing works focus more on learning with the explicit prior graph structure, while ignoring potential information from the implicit graph structure, yielding incomplete structure modeling. Some recent works attempt to learn the intrinsic or implicit graph structure directly while lacking a way to combine explicit prior structure with implicit structure together. In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with the graph structure. RGSL consists of two innovative modules. First, we derive an implicit dense similarity matrix through node embedding, and learn the sparse graph structure using the Regularized Graph Generation (RGG) based on the Gumbel Softmax trick. Second, we propose a Laplacian Matrix Mixed-up Module (LM3) to fuse the explicit graph and implicit graph together. We conduct experiments on three real-word datasets. Results show that the proposed RGSL model outperforms existing graph forecasting algorithms with a notable margin, while learning meaningful graph structure simultaneously. Our code and models are made publicly available at https://github.com/alipay/RGSL.git.