Link Prediction under Heterophily: A Physics-Inspired Graph Neural Network Approach

arXiv:2402.14802v1 Announce Type: new
Abstract: In the past years, Graph Neural Networks (GNNs) have become the `de facto' standard in various deep learning domains, thanks to their flexibility in modeling real-world phenomena represented as graphs. However, the message-passing mechanism of GNNs faces challenges in learnability and expressivity, hindering high performance on heterophilic graphs, where adjacent nodes frequently have different labels. Most existing solutions addressing these challenges are primarily confined to specific benchmarks focused on node classification tasks. This narrow focus …

abstract arxiv become challenges cs.ir cs.lg cs.si deep learning domains flexibility gnns graph graph neural network graph neural networks graphs link prediction modeling network networks neural network neural networks performance physics prediction standard type world