mlsanityData to 7 Oct 2026

A Survey on Graph Structure Learning: Progress and Opportunities

arXiv 2103.03036 ↗First posted 4 Mar 2021cs.LG cs.SIcited by 70

Not on the map. Why?

Abstract (arXiv)

Graphs are widely used to describe real-world objects and their interactions. Graph Neural Networks (GNNs) as a de facto model for analyzing graphstructured data, are highly sensitive to the quality of the given graph structures. Therefore, noisy or incomplete graphs often lead to unsatisfactory representations and prevent us from fully understanding the mechanism underlying the system. In pursuit of an optimal graph structure for downstream tasks, recent studies have sparked an effort around the central theme of Graph Structure Learning (GSL), which aims to jointly learn an optimized graph structure and corresponding graph representations. In the presented survey, we broadly review recent progress in GSL methods. Specifically, we first formulate a general pipeline of GSL and review state-of-the-art methods classified by the way of modeling graph structures, followed by applications of GSL across domains. Finally, we point out some issues in current studies and discuss future directions.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 4 Mar 2021.

Builds on

24 of 52 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2020A Generalization of Transformer Networks to Graphscited by 653
  7. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  8. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  9. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  10. 2019Diffusion Improves Graph Learningcited by 414
  11. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  12. 2018Adversarial Attack on Graph Structured Datacited by 300
12 more
  1. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  2. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  3. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  4. 2016How to learn a graph from smooth signalscited by 146
  5. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  6. 2018Learning graphs from data: A signal representation perspectivecited by 119
  7. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  8. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  9. 2018Attention Models in Graphs: A Surveycited by 41
  10. 2019Graph Representation Learning via Hard and Channel-Wise Attention Networkscited by 18
  11. 2020CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learningcited by 18
  12. 2020Class-Attentive Diffusion Network for Semi-Supervised Classificationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 13; 2023: 14; 2024: 22; 2025: 10; 2026: 11.

70 papers.

Sort:

By area:

  1. 2022DiffWire: Inductive Graph Rewiring via the Lov'asz Boundcited by 79
  2. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  3. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  4. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  5. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  6. 2023GSLB: The Graph Structure Learning Benchmarkcited by 49
  7. 2023Towards Understanding the Generalization of Graph Neural Networkscited by 41
  8. 2024A Comprehensive Survey on Data Augmentationcited by 38
  9. 2022T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillationcited by 32
  10. 2022Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Modelscited by 29
  11. 2024The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challengescited by 29
  12. 2022Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approachcited by 23
38 more
  1. 2023Data-centric Graph Learning: A Surveycited by 22
  2. 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
  3. 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
  4. 2024DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learningcited by 14
  5. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  6. 2023Molecular Property Prediction Based on Graph Structure Learningcited by 13
  7. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  8. 2024Graph Neural Networks for Brain Graph Learning: A Surveycited by 13
  9. 2024Graph Neural Networks in Histopathology: Emerging Trends and Future Directionscited by 13
  10. 2024CTINexus: Automatic Cyber Threat Intelligence Knowledge Graph Construction Using Large Language Modelscited by 12
  11. 2022Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcitycited by 11
  12. 2023Graph Convolution Based Efficient Re-Ranking for Visual Retrievalcited by 11
  13. 2022Spatio-Temporal Dynamic Graph Relation Learning for Urban Metro Flow Predictioncited by 9
  14. 2024Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Drivingcited by 9
  15. 2023Adversarially Robust Neural Architecture Search for Graph Neural Networkscited by 7
  16. 2023STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Predictioncited by 7
  17. 2023Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecastingcited by 7
  18. 2024DGDNN: Decoupled Graph Diffusion Neural Network for Stock Movement Predictioncited by 7
  19. 2024Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clientscited by 7
  20. 2023Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphscited by 6
  21. 2023Uncertainty-Aware Robust Learning on Noisy Graphscited by 6
  22. 2024Continual Traffic Forecasting via Mixture of Expertscited by 6
  23. 2022Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligencecited by 5
  24. 2022DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learningcited by 4
  25. 2024Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problemcited by 4
  26. 2023Contaminated Multivariate Time-Series Anomaly Detection with Spatio-Temporal Graph Conditional Diffusion Modelscited by 3
  27. 2024CNN2GNN: How to Bridge CNN with GNNcited by 3
  28. 2024Graph Structure Refinement with Energy-based Contrastive Learningcited by 3
  29. 2025Incomplete Graph Learning: A Comprehensive Surveycited by 3
  30. 2025Persistent Homology-induced Graph Ensembles for Time Series Regressionscited by 3
  31. 2025Neuro-Argumentative Learning with Case-Based Reasoningcited by 3
  32. 2023Everything Perturbed All at Once: Enabling Differentiable Graph Attackscited by 2
  33. 2024SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformerscited by 2
  34. 2022ASGNN: Graph Neural Networks with Adaptive Structurecited by 1
  35. 2024Active Learning for Graphs with Noisy Structurescited by 1
  36. 2024Learning Social Graph for Inactive User Recommendationcited by 1
  37. 2024Recovering Time-Varying Networks From Single-Cell Datacited by 1
  38. 2024Geometric Graph Neural Network Modeling of Human Interactions in Crowded Environmentscited by 1

50 most cited of 70 All 70 (JSON)