Simple and Efficient Heterogeneous Temporal Graph Neural Network
This addresses the need for efficient and accurate modeling of spatio-temporal interactions in heterogeneous temporal graphs, which are common in real-world applications, and is incremental as it builds on existing attention-based neural networks.
The paper tackles the problem of representation learning on heterogeneous temporal graphs by proposing SE-HTGNN, which integrates temporal modeling into spatial learning via a dynamic attention mechanism, achieving up to 10x speed-up over state-of-the-art methods while maintaining the best forecasting accuracy.
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.