Higher-order Structure Boosts Link Prediction on Temporal Graphs
This work addresses efficiency and expressiveness limitations in temporal graph learning for link prediction, offering a domain-specific improvement.
The paper tackles the problem of temporal graph neural networks overlooking higher-order structures and efficiency bottlenecks by proposing a Higher-order structure Temporal Graph Neural Network (HTGN) that incorporates hypergraph representations, achieving superior dynamic link prediction performance and reducing memory costs by up to 50% compared to existing methods.
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.