GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy

arXiv:2312.09708v2 Announce Type: replace
Abstract: Graph neural networks (GNNs) have shown advantages in graph-based analysis tasks. However, most existing methods have the homogeneity assumption and show poor performance on heterophilic graphs, where the linked nodes have dissimilar features and different class labels, and the semantically related nodes might be multi-hop away. To address this limitation, this paper presents GraphRARE, a general framework built upon node relative entropy and deep reinforcement learning, to strengthen the expressive capability of GNNs. An innovative …

abstract advantages analysis arxiv class cs.ai cs.lg entropy features gnns graph graph-based graph neural network graph neural networks graphs however labels network networks neural network neural networks nodes performance reinforcement reinforcement learning show tasks type