High-order Graph Neural Networks with Common Neighbor Awareness for Link Prediction
This work addresses a specific bottleneck in dynamic graph learning for link prediction, offering an incremental improvement by enhancing common neighbor awareness.
The paper tackles the problem of link prediction in dynamic graphs by addressing the neglect of common neighbor interactions in existing dynamic graph neural networks, proposing HGNN-CNA which incorporates multi-hop common neighbors and fuses correlation into message-passing, resulting in significant accuracy gains over state-of-the-art models on three real datasets.
Link prediction is a fundamental task in dynamic graph learning (DGL), inherently shaped by the topology of the DG. Recent advancements in dynamic graph neural networks (DGNN), primarily by modeling the relationships among nodes via a message passing scheme, have significantly improved link prediction performance. However, DGNNs heavily rely on the pairwise node interactions, which neglect the common neighbor interaction in DGL. To address this limitation, we propose a High-order Graph Neural Networks with Common Neighbor Awareness (HGNN-CNA) for link prediction with two-fold ideas: a) estimating correlation score by considering multi-hop common neighbors for capturing the complex interaction between nodes; b) fusing the correlation into the message-passing process to consider common neighbor interaction directly in DGL. Experimental results on three real DGs demonstrate that the proposed HGNN-CNA acquires a significant accuracy gain over several state-of-the-art models on the link prediction task.