Attribute-Enhanced Similarity Ranking for Sparse Link Prediction

TL;DR

This paper introduces Gelato, a similarity-based link prediction method that leverages node attributes and advanced sampling techniques to outperform GNNs in sparse, real-world graph scenarios.

Contribution

The paper proposes Gelato, a novel link prediction approach combining attribute-enhanced similarity, ranking loss, and efficient negative sampling, addressing GNN limitations in sparse graphs.

Findings

Gelato outperforms GNN-based methods in sparse link prediction tasks.

Attribute integration improves prediction accuracy in sparse graphs.

Efficient negative sampling enhances training effectiveness.

Abstract

Link prediction is a fundamental problem in graph data. In its most realistic setting, the problem consists of predicting missing or future links between random pairs of nodes from the set of disconnected pairs. Graph Neural Networks (GNNs) have become the predominant framework for link prediction. GNN-based methods treat link prediction as a binary classification problem and handle the extreme class imbalance -- real graphs are very sparse -- by sampling (uniformly at random) a balanced number of disconnected pairs not only for training but also for evaluation. However, we show that the reported performance of GNNs for link prediction in the balanced setting does not translate to the more realistic imbalanced setting and that simpler topology-based approaches are often better at handling sparsity. These findings motivate Gelato, a similarity-based link-prediction method that applies (1) graph learning based on node attributes to enhance a topological heuristic, (2) a ranking loss for addressing class imbalance, and (3) a negative sampling scheme that efficiently selects hard training pairs via graph partitioning. Experiments show that Gelato outperforms existing GNN-based alternatives.