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

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.

arXiv commentto be published in IJCAI2022

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions
• Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
• Deep Multi-View Spatiotemporal Virtual Graph Neural Network for Significant Citywide Ride-hailing Demand Prediction
• Demand Forecasting from Spatiotemporal Data with Graph Networks and Temporal-Guided Embedding

Cited by in corpus (1)

• Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting