mlsanityData to 7 Oct 2026

Bayesian Graph Neural Networks with Adaptive Connection Sampling

arXiv 2006.04064 ↗First posted 7 Jun 2020cs.LG stat.MLcited by 81

Not on the map. Why?

Abstract (arXiv)

We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs. The proposed framework not only alleviates over-smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs. Instead of using fixed sampling rates or hand-tuning them as model hyperparameters in existing stochastic regularization methods, our adaptive connection sampling can be trained jointly with GNN model parameters in both global and local fashions. GNN training with adaptive connection sampling is shown to be mathematically equivalent to an efficient approximation of training Bayesian GNNs. Experimental results with ablation studies on benchmark datasets validate that adaptively learning the sampling rate given graph training data is the key to boost the performance of GNNs in semi-supervised node classification, less prone to over-smoothing and over-fitting with more robust prediction.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 19; 2023: 15; 2024: 15; 2025: 13; 2026: 6.

81 papers.

Sort:

By area:

  1. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 246
  2. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  3. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  4. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  5. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  6. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  7. 2022A Survey on Graph Representation Learning Methodscited by 66
  8. 2023Demystifying Oversmoothing in Attention-Based Graph Neural Networkscited by 47
  9. 2021Sampling methods for efficient training of graph convolutional networks: A surveycited by 40
  10. 2022What Makes Graph Neural Networks Miscalibrated?cited by 39
  11. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  12. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
38 more
  1. 2023Class-Imbalanced Graph Learning without Class Rebalancingcited by 29
  2. 2022Distribution Free Prediction Sets for Node Classificationcited by 28
  3. 2023Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreachingcited by 23
  4. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  5. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  6. 2025Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learningcited by 18
  7. 2021Graph Classification by Mixture of Diverse Expertscited by 16
  8. 2022JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networkscited by 14
  9. 2022A General Framework for quantifying Aleatoric and Epistemic uncertainty in Graph Neural Networkscited by 12
  10. 2022Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagationcited by 12
  11. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  12. 2022Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attackcited by 10
  13. 2024Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networkscited by 8
  14. 2024Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equationscited by 8
  15. 2021TyXe: Pyro-based Bayesian neural nets for Pytorchcited by 6
  16. 2022A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphscited by 6
  17. 2022Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-seriescited by 5
  18. 2022Retention Time Prediction for Chromatographic Enantioseparation by Quantile Geometry-enhanced Graph Neural Networkcited by 5
  19. 2023Homological Neural Networks: A Sparse Architecture for Multivariate Complexitycited by 5
  20. 2024MultiMax: Sparse and Multi-Modal Attention Learningcited by 5
  21. 2021Training Graph Neural Networks by Graphon Estimationcited by 4
  22. 2022Asynchronous Neural Networks for Learning in Graphscited by 4
  23. 2022Node Copying: A Random Graph Model for Effective Graph Samplingcited by 4
  24. 2023GNN-Ensemble: Towards Random Decision Graph Neural Networkscited by 4
  25. 2023GNNPipe: Scaling Deep GNN Training with Pipelined Model Parallelismcited by 4
  26. 2023On the Temperature of Bayesian Graph Neural Networks for Conformal Predictioncited by 4
  27. 2024Improving the interpretability of GNN predictions through conformal-based graph sparsificationcited by 4
  28. 2024Oversmoothing Alleviation in Graph Neural Networks: A Survey and Unified Viewcited by 4
  29. 2021Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecastingcited by 3
  30. 2021Bayesian Graph Contrastive Learningcited by 3
  31. 2022MoReL: Multi-omics Relational Learningcited by 3
  32. 2023A Comprehensive Survey on Graph Summarization with Graph Neural Networkscited by 3
  33. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  34. 2024Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphscited by 3
  35. 2024Foundations and Frontiers of Graph Learning Theorycited by 3
  36. 2024xAI-Drop: Don't Use What You Cannot Explaincited by 3
  37. 2024Improving Graph Neural Networks by Learning Continuous Edge Directionscited by 3
  38. 2024Conditional Prediction ROC Bands for Graph Classificationcited by 3

50 most cited of 81 All 81 (JSON)