mlsanityData to 14 Oct 2026

Learning Discrete Structures for Graph Neural Networks

arXiv 1903.11960 ↗First posted 28 Mar 2019cs.LG stat.MLcited by 231

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such a graph-structure is available. In practice, however, real-world graphs are often noisy and incomplete or might not be available at all. With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph. This allows one to apply GCNs not only in scenarios where the given graph is incomplete or corrupted but also in those where a graph is not available. We conduct a series of experiments that analyze the behavior of the proposed method and demonstrate that it outperforms related methods by a significant margin.

Key facts. Cited by 231 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 39; 2022: 39; 2023: 53; 2024: 48; 2025: 22; 2026: 30.

231 papers.

Sort:

By area:

  1. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  2. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  3. 2021Graph Condensation for Graph Neural Networkscited by 150
  4. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 133
  5. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  6. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  7. 2023GraphText: Graph Reasoning in Text Spacecited by 111
  8. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 110
  9. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  10. 2021Implicit MLE: Backpropagating Through Discrete Exponential Family Distributionscited by 98
  11. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  12. 2023DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusioncited by 87
38 more
  1. 2021Beltrami Flow and Neural Diffusion on Graphscited by 84
  2. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  3. 2021Mining Latent Structures for Multimedia Recommendationcited by 79
  4. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  5. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 71
  6. 2022FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generationcited by 67
  7. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 67
  8. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 62
  9. 2023GSLB: The Graph Structure Learning Benchmarkcited by 50
  10. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  11. 2024Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Spacecited by 43
  12. 2024A Comprehensive Survey on Data Augmentationcited by 40
  13. 2021RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecastingcited by 36
  14. 2021From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligencecited by 35
  15. 2023SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimizationcited by 35
  16. 2022Multi-modal Graph Learning for Disease Predictioncited by 34
  17. 2024GraphEdit: Large Language Models for Graph Structure Learningcited by 33
  18. 2022Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashingcited by 31
  19. 2022Evidence-aware Fake News Detection with Graph Neural Networkscited by 30
  20. 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learningcited by 30
  21. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  22. 2022MGAE: Masked Autoencoders for Self-Supervised Learning on Graphscited by 28
  23. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  24. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  25. 2023Learning Strong Graph Neural Networks with Weak Informationcited by 25
  26. 2021Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Seriescited by 24
  27. 2023Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreachingcited by 24
  28. 2022Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approachcited by 23
  29. 2022Transformers over Directed Acyclic Graphscited by 23
  30. 2022Latent Graph Inference using Product Manifoldscited by 23
  31. 2023Learning How to Propagate Messages in Graph Neural Networkscited by 23
  32. 2021Graph Contrastive Learning for Anomaly Detectioncited by 22
  33. 2022Sparse Graph Learning from Spatiotemporal Time Seriescited by 22
  34. 2022Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graphcited by 22
  35. 2023Data-centric Graph Learning: A Surveycited by 22
  36. 2021Graph Sanitation with Application to Node Classificationcited by 20
  37. 2021Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 20
  38. 2022Compact Graph Structure Learning via Mutual Information Compressioncited by 20

50 most cited of 231 All 231 (JSON)