Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
This addresses a specific bottleneck in graph learning for link prediction, offering a novel method that improves over simple heuristic approaches.
The paper tackles the problem of GNNs performing poorly in link prediction due to reliance on smoothed node features rather than structural information, and proposes Neo-GNNs that learn structural features from adjacency matrices to achieve state-of-the-art performance on Open Graph Benchmark datasets.
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.