Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

TL;DR

Neo-GNNs are a novel graph neural network model that explicitly incorporate neighborhood overlap information to improve link prediction accuracy, outperforming existing methods on benchmark datasets.

Contribution

The paper introduces Neo-GNNs, a new GNN architecture that leverages structural neighborhood overlap features for enhanced link prediction performance.

Findings

Neo-GNNs achieve state-of-the-art results on OGB datasets.

Neo-GNNs effectively handle overlapped multi-hop neighborhoods.

The method outperforms traditional heuristic and GNN-based approaches.

Abstract

Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data. They have shown significant improvements over traditional heuristic methods in various tasks such as node classification and graph classification. However, since GNNs heavily rely on smoothed node features rather than graph structure, they often show poor performance than simple heuristic methods in link prediction where the structural information, e.g., overlapped neighborhoods, degrees, and shortest paths, is crucial. To address this limitation, we propose Neighborhood Overlap-aware Graph Neural Networks (Neo-GNNs) that learn useful structural features from an adjacency matrix and estimate overlapped neighborhoods for link prediction. Our Neo-GNNs generalize neighborhood overlap-based heuristic methods and handle overlapped multi-hop neighborhoods. Our extensive experiments on Open Graph Benchmark datasets (OGB) demonstrate that Neo-GNNs consistently achieve state-of-the-art performance in link prediction. Our code is publicly available at https://github.com/seongjunyun/Neo_GNNs.