mlsanityData to 14 Oct 2026

SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization

arXiv 2303.09778 ↗First posted 17 Mar 2023cs.LG cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are de facto solutions to structural data learning. However, it is susceptible to low-quality and unreliable structure, which has been a norm rather than an exception in real-world graphs. Existing graph structure learning (GSL) frameworks still lack robustness and interpretability. This paper proposes a general GSL framework, SE-GSL, through structural entropy and the graph hierarchy abstracted in the encoding tree. Particularly, we exploit the one-dimensional structural entropy to maximize embedded information content when auxiliary neighbourhood attributes are fused to enhance the original graph. A new scheme of constructing optimal encoding trees is proposed to minimize the uncertainty and noises in the graph whilst assuring proper community partition in hierarchical abstraction. We present a novel sample-based mechanism for restoring the graph structure via node structural entropy distribution. It increases the connectivity among nodes with larger uncertainty in lower-level communities. SE-GSL is compatible with various GNN models and enhances the robustness towards noisy and heterophily structures. Extensive experiments show significant improvements in the effectiveness and robustness of structure learning and node representation learning.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 43 of its 70 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

43 of 70 references.

References · 43

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  8. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  9. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  10. 2020Simple and Deep Graph Convolutional Networkscited by 860
  11. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  12. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
31 more
  1. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  2. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  3. 2019Multi-scale Attributed Node Embeddingcited by 548
  4. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  5. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  6. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  7. 2019Diffusion Improves Graph Learningcited by 414
  8. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  9. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  10. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
  11. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  12. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  13. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  14. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  15. 2020Graph Information Bottleneckcited by 168
  16. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 167
  17. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  18. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  19. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  20. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  21. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  22. 2019Certifiable Robustness to Graph Perturbationscited by 62
  23. 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
  24. 2021Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddingscited by 49
  25. 2021Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networkscited by 38
  26. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  27. 2022Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashingcited by 31
  28. 2019Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networkscited by 23
  29. 2020CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learningcited by 18
  30. 2021Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networkscited by 13
  31. 2021An Information-theoretic Perspective of Hierarchical Clusteringcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 13; 2025: 10; 2026: 6.

35 papers.

Sort:

By area:

  1. 2024GraphEdit: Large Language Models for Graph Structure Learningcited by 33
  2. 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learningcited by 30
  3. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  4. 2024LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clusteringcited by 21
  5. 2024DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashingcited by 16
  6. 2024SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detectioncited by 16
  7. 2024Probabilistic Graph Rewiring via Virtual Nodescited by 15
  8. 2023Hierarchical State Abstraction Based on Structural Information Principlescited by 14
  9. 2023MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimizationcited by 13
  10. 2023Adversarial Socialbots Modeling Based on Structural Information Principlescited by 10
  11. 2024Exploring the Potential of Large Language Models for Heterophilic Graphscited by 10
  12. 2023Unsupervised Skin Lesion Segmentation via Structural Entropy Minimization on Multi-Scale Superpixel Graphscited by 7
23 more
  1. 2025HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphscited by 5
  2. 2024IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighborscited by 4
  3. 2024Effective Exploration Based on the Structural Information Principlescited by 4
  4. 2025ASIL: Augmented Structural Information Learning for Deep Graph Clustering in Hyperbolic Spacecited by 4
  5. 2025Unsupervised Graph Clustering with Deep Structural Entropycited by 4
  6. 2024Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learningcited by 3
  7. 2024Rumor Detection on Social Media with Temporal Propagation Structure Optimizationcited by 3
  8. 2025Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learningcited by 2
  9. 2025Principled Data Augmentation for Learning to Solve Quadratic Programming Problemscited by 2
  10. 2025STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputationcited by 2
  11. 2024Motif-driven Subgraph Structure Learning for Graph Classificationcited by 1
  12. 2024Structural Entropy Guided Probabilistic Codingcited by 1
  13. 2025GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classificationcited by 1
  14. 2025Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learningcited by 1
  15. 2024Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Spacecited by 0
  16. 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approachcited by 0
  17. 2025When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approachcited by 0
  18. 2026LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMscited by 0
  19. 2026Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compressioncited by 0
  20. 2026Targeted Adversarial Traffic Generation : Black-box Approach to Evade Intrusion Detection Systems in IoT Networkscited by 0
  21. 2026Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspectivecited by 0
  22. 2026Informative Graph Structure Learningcited by 0
  23. 2026OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradationcited by 0