A Topological Perspective on Demystifying GNN-Based Link Prediction Performance

Yu Wang, Tong Zhao, Yuying Zhao, Yunchao Liu, Xueqi Cheng, Neil Shah, Tyler Derr

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Link prediction; Graph Topology; Graph Neural Network ; Cold-start Issues

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a new node-level topological metric, Topological Concentration, to understand the relationship between node local topology and its GNNs' link prediction performance

Abstract: Graph Neural Networks (GNNs) have shown great promise in learning node embeddings for link prediction (LP). While numerous studies improve the overall GNNs' LP performance, none have explored their varying performance across different nodes and the underlying reasons. To this end, we demystify which nodes perform better from the perspective of their local topology. Despite the widespread belief that low-degree nodes exhibit worse LP performance, we surprisingly observe an inconsistent performance trend. This prompts us to propose a node-level metric, Topological Concentration (TC), based on the intersection of the local subgraph of each node with the ones of its neighbors. We empirically demonstrate that TC correlates with LP performance more than other node-level topological metrics, better identifying low-performing nodes than using degree. With TC, we discover a novel topological distribution shift issue in which nodes' newly joined neighbors tend to become less interactive with their existing neighbors, compromising the generalizability of node embeddings for LP at testing time. To make the computation of TC scalable, We further propose Approximated Topological Concentration (ATC) and justify its efficacy in approximating TC with reduced computation complexity. Given the positive correlation between node TC and its LP performance, we explore the potential of boosting LP performance via enhancing TC by re-weighting edges in the message-passing and discuss its effectiveness with limitations. Our code is publicly available at https://github.com/YuWVandy/Topo_LP_GNN.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 5889