Simple and Efficient Heterogeneous Temporal Graph Neural Network

TL;DR

This paper introduces SE-HTGNN, a novel, efficient neural network for heterogeneous temporal graphs that integrates temporal and spatial learning, significantly improving speed and accuracy over existing methods.

Contribution

The paper proposes a new paradigm that combines temporal and spatial learning in HTGs using a dynamic attention mechanism and leverages large language models for enhanced understanding.

Findings

Up to 10x faster than state-of-the-art methods

Achieves superior forecasting accuracy

Effectively captures spatio-temporal interactions

Abstract

Heterogeneous temporal graphs (HTGs) are ubiquitous data structures in the real world. Recently, to enhance representation learning on HTGs, numerous attention-based neural networks have been proposed. Despite these successes, existing methods rely on a decoupled temporal and spatial learning paradigm, which weakens interactions of spatio-temporal information and leads to a high model complexity. To bridge this gap, we propose a novel learning paradigm for HTGs called Simple and Efficient Heterogeneous Temporal Graph N}eural Network (SE-HTGNN). Specifically, we innovatively integrate temporal modeling into spatial learning via a novel dynamic attention mechanism, which retains attention information from historical graph snapshots to guide subsequent attention computation, thereby improving the overall discriminative representations learning of HTGs. Additionally, to comprehensively and adaptively understand HTGs, we leverage large language models to prompt SE-HTGNN, enabling the model to capture the implicit properties of node types as prior knowledge. Extensive experiments demonstrate that SE-HTGNN achieves up to 10x speed-up over the state-of-the-art and latest baseline while maintaining the best forecasting accuracy.