Higher-order Structure Boosts Link Prediction on Temporal Graphs

TL;DR

This paper introduces a higher-order structure-aware temporal graph neural network that improves link prediction accuracy and efficiency by incorporating hypergraph representations and group interactions.

Contribution

It proposes a novel HTGN model that captures higher-order structures in temporal graphs, enhancing expressiveness and reducing memory costs.

Findings

HTGN outperforms existing methods in dynamic link prediction.

The model reduces memory costs by up to 50%.

Theoretical analysis confirms increased expressiveness.

Abstract

Temporal Graph Neural Networks (TGNNs) have gained growing attention for modeling and predicting structures in temporal graphs. However, existing TGNNs primarily focus on pairwise interactions while overlooking higher-order structures that are integral to link formation and evolution in real-world temporal graphs. Meanwhile, these models often suffer from efficiency bottlenecks, further limiting their expressive power. To tackle these challenges, we propose a Higher-order structure Temporal Graph Neural Network, which incorporates hypergraph representations into temporal graph learning. In particular, we develop an algorithm to identify the underlying higher-order structures, enhancing the model's ability to capture the group interactions. Furthermore, by aggregating multiple edge features into hyperedge representations, HTGN effectively reduces memory cost during training. We theoretically demonstrate the enhanced expressiveness of our approach and validate its effectiveness and efficiency through extensive experiments on various real-world temporal graphs. Experimental results show that HTGN achieves superior performance on dynamic link prediction while reducing memory costs by up to 50\% compared to existing methods.