Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancement

TL;DR

This paper investigates the impact of long-tailed degree distribution on GNN-based link prediction, revealing the importance of common neighbors and proposing a framework to enhance tail node pair prediction by augmenting common neighbors.

Contribution

It introduces LTLP, a novel framework that improves link prediction for tail node pairs by augmenting common neighbors and aligning representations within categories.

Findings

Common neighbors strongly correlate with prediction accuracy.

Tail node pairs perform worse due to fewer common neighbors.

LTLP improves link prediction performance for tail node pairs.

Abstract

Link prediction, as a fundamental task for graph neural networks (GNNs), has boasted significant progress in varied domains. Its success is typically influenced by the expressive power of node representation, but recent developments reveal the inferior performance of low-degree nodes owing to their sparse neighbor connections, known as the degree-based long-tailed problem. Will the degree-based long-tailed distribution similarly constrain the efficacy of GNNs on link prediction? Unexpectedly, our study reveals that only a mild correlation exists between node degree and predictive accuracy, and more importantly, the number of common neighbors between node pairs exhibits a strong correlation with accuracy. Considering node pairs with less common neighbors, i.e., tail node pairs, make up a substantial fraction of the dataset but achieve worse performance, we propose that link prediction also faces the long-tailed problem. Therefore, link prediction of GNNs is greatly hindered by the tail node pairs. After knowing the weakness of link prediction, a natural question is how can we eliminate the negative effects of the skewed long-tailed distribution on common neighbors so as to improve the performance of link prediction? Towards this end, we introduce our long-tailed framework (LTLP), which is designed to enhance the performance of tail node pairs on link prediction by increasing common neighbors. Two key modules in LTLP respectively supplement high-quality edges for tail node pairs and enforce representational alignment between head and tail node pairs within the same category, thereby improving the performance of tail node pairs.