Lune

ICDE2024Top-tier venue

GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy

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

Abstract

Graph neural networks (GNNs) have shown ad-vantages 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 en-tropy. 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily cites Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
  • GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily cites Geom-GCN: Geometric Graph Convolutional Networks
  • Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs cites Geom-GCN: Geometric Graph Convolutional Networks
  • Universal Graph Convolutional Networks cites Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
  • Universal Graph Convolutional Networks cites Geom-GCN: Geometric Graph Convolutional Networks
  • Powerful Graph Convolutional Networks with Adaptive Propagation Mechanism for Homophily and Heterophily cites Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
  • Powerful Graph Convolutional Networks with Adaptive Propagation Mechanism for Homophily and Heterophily cites Geom-GCN: Geometric Graph Convolutional Networks
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Towards Fair Graph Neural Networks via Graph Counterfactual Without Sensitive AttributesXuemin Wang, Tianlong Gu, Xuguang Bao, Liang ChangICDE 2025 · 3 citations
  2. GraphPrompter: Multi-Stage Adaptive Prompt Optimization for Graph In-Context LearningRui Lv, Zaixi Zhang, Kai Zhang, Qi Liu et al.ICDE 2025 · 1 citation

Builds on21

  1. Beyond Homophily in Graph Neural Networks: Current Limitations and Effective DesignsJiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann et al.NeurIPS 2020 · 1,490 citations
  2. Geom-GCN: Geometric Graph Convolutional NetworksHongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei et al.ICLR 2020 · 1,445 citations
  3. GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and HeterophilyLun Du, Xiaozhou Shi, Qiang Fu, Xiaojun Ma et al.WWW 2022 · 155 citations
  4. Universal Graph Convolutional NetworksDi Jin, Zhizhi Yu, Cuiying Huo, Rui Wang et al.NeurIPS 2021 · 132 citations
  5. Powerful Graph Convolutional Networks with Adaptive Propagation Mechanism for Homophily and HeterophilyTao Wang, Di Jin, Rui Wang, Dongxiao He et al.AAAI 2022 · 126 citations

Related papers

  1. Boosting Graph Convolution with Disparity-induced Structural RefinementSujia Huang, Yueyang Pi, Tong Zhang, Wenzhe Liu et al.WWW 2025 · 1 citation
  2. Is Homophily a Necessity for Graph Neural Networks?Yao Ma, Xiaorui Liu, Neil Shah, Jiliang TangICLR 2022 · 295 citations
  3. Beyond Homophily: Reconstructing Structure for Graph-agnostic ClusteringErlin Pan, Zhao KangICML 2023 · 67 citations
  4. Node Classification Beyond Homophily: Towards a General SolutionZhe Xu, Yuzhong Chen, Qinghai Zhou, Yuhang Wu et al.KDD 2023 · 17 citations
  5. Graph Neural Networks with HeterophilyJiong Zhu, Ryan A. Rossi, Anup Rao, Tung Mai et al.AAAI 2021 · 393 citations
Dusk over the sea between two cliffs drawn in fine vertical lines