GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention

Abstract

Forecasting graph-based, time-dependent data has broad practical applications but presents challenges. Effective models must capture both spatial and temporal dependencies in the data, while also incorporating auxiliary information to enhance prediction accuracy. In this paper, we identify limitations in current state-of-the-art models regarding temporal dependency handling. To overcome this, we introduce GSA-Forecaster, a new deep learning model designed for forecasting in graph-based, time-dependent contexts. GSA-Forecaster utilizes graph sequence attention, a new attention mechanism proposed in this paper, to effectively manage temporal dependencies. GSA-Forecaster integrates the data's graph structure directly into its architecture, addressing spatial dependencies. Additionally, it incorporates auxiliary information to refine its predictions further. We validate its performance using real-world graph-based, time-dependent datasets, where it demonstrates superior effectiveness compared to existing state-of-the-art models.

References in corpus (9)

• Language Models are Few-Shot Learners
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Graph Transformer Networks
• Generating Long Sequences with Sparse Transformers
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
• Topology Adaptive Graph Convolutional Networks
• Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
• Sparse inverse covariance estimation with the lasso
• Forecaster: A Graph Transformer for Forecasting Spatial and Time-Dependent Data