A topological perspective on demystifying gnn-based link prediction performance
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 …
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 …
[引用][C] A topological perspective on demystifying gnn-based link prediction performance
A Topological Perspective on Demystifying GNN-Based Link Prediction Performance |
OpenReview … A Topological Perspective on Demystifying GNN-Based Link Prediction
Performance …
OpenReview … A Topological Perspective on Demystifying GNN-Based Link Prediction
Performance …
以上显示的是最相近的搜索结果。 查看全部搜索结果