Tech Xplore

HarmonyGNN boosts graph AI accuracy on four tough benchmarks by up to 9.6%

Researchers have demonstrated a new training technique that significantly improves the accuracy of graph neural networks ...
IEEE

Graph Neural Networks for Graphs With Heterophily: A Survey

Abstract: Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriad graph analytic tasks and applications. Most GNNs rely on the homophily assumption ...
IEEE

Uncertainty-Aware Graph Neural Networks: A Multihop Evidence Fusion Approach

Abstract: Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertainty of ...