Can I read A Topological Perspective on Demystifying GNN-Based Link Prediction Performance on EtoBox?

A Topological Perspective on Demystifying GNN-Based Link Prediction Performance by Wang, Yu; Zhao, Tong; Zhao, Yuying; Liu, Yunchao; Cheng, Xueqi; Shah, Neil; Derr, Tyler is a scholarly article available to read on EtoBox.

What is A Topological Perspective on Demystifying GNN-Based Link Prediction Performance about?

Graph Neural Networks (GNNs) have shown great promise in learning node embeddings for link prediction (LP). While numerous studies aim to improve the overall LP performance of GNNs, none have explored its varying performance across different nodes and its underlying reasons. To this end, we aim to demystify which nodes will perform better from the perspective of their local topology. Despite the widespread belief that low-degree nodes exhibit poorer LP performance, our empirical findings provide nuances to this viewpoint and prompt us to propose a better 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 has a higher correlation with LP performance than other node-level topological metrics like degree and subgraph density, offering a better way to identify low-performing nodes than using cold-start. With TC, we discover a novel topological distribution shift issue in which newly joined neighbors of a node tend to become less interactive with that node's existing neighbors, compromising the generalizability of node embeddings for LP at testing time. To make the comput

Author

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

Published

2023

Language

EN