Papers › GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy

GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy

15 Dec 2023arXiv:2312.09708archive 2025-07-28

Tianhao Peng, Wenjun Wu, Haitao Yuan, Zhifeng Bao, Zhao Pengrui, Xin Yu, Xuetao Lin, Yu Liang, Yanjun Pu

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 node relative entropy, which considers node features and structural similarity, is used to measure mutual information between node pairs. In addition, to avoid the sub-optimal solutions caused by mixing useful information and noises of remote nodes, a deep reinforcement learning-based algorithm is developed to optimize the graph topology. This algorithm selects informative nodes and discards noisy nodes based on the defined node relative entropy. Extensive experiments are conducted on seven real-world datasets. The experimental results demonstrate the superiority of GraphRARE in node classification and its capability to optimize the original graph topology.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep Reinforcement LearningGraph Neural NetworkNode ClassificationReinforcement Learningreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Chameleon GraphSAGE-RARE (λ=1.0) Accuracy 69.28±1.90 #33 of 61 Archive leaderboard report
Node Classification Cornell H2GCN-RARE (λ=1.0) Accuracy 87.84±4.05 #4 of 60 Archive leaderboard report
Node Classification Squirrel GCN-RARE (λ=1.0) Accuracy 55.90±1.39 #35 of 59 Archive leaderboard report
Node Classification Texas H2GCN-RARE (λ=1.0) Accuracy 86.76±5.80 #17 of 62 Archive leaderboard report
Node Classification Wisconsin H2GCN-RARE (λ=1.0) Accuracy 90.00±2.97 #4 of 63 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections