mlsanityData to 7 Oct 2026

Metropolis-Hastings Data Augmentation for Graph Neural Networks

arXiv 2203.14082 ↗First posted 26 Mar 2022cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a prevalent remedy to improve the generalization ability of models in many domains. However, due to the non-Euclidean nature of data space and the dependencies between samples, designing effective augmentation on graphs is challenging. In this paper, we propose a novel framework Metropolis-Hastings Data Augmentation (MH-Aug) that draws augmented graphs from an explicit target distribution for semi-supervised learning. MH-Aug produces a sequence of augmented graphs from the target distribution enables flexible control of the strength and diversity of augmentation. Since the direct sampling from the complex target distribution is challenging, we adopt the Metropolis-Hastings algorithm to obtain the augmented samples. We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 29 of its 37 references that are in the map. First posted on arXiv 26 Mar 2022.

Builds on

29 of 37 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  11. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  12. 2016Variational Graph Auto-Encoderscited by 1,373
17 more
  1. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  2. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  3. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  4. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  5. 2018Link Prediction Based on Graph Neural Networkscited by 829
  6. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  7. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  8. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  9. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  10. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  11. 2017Representation Learning on Graphs: Methods and Applicationscited by 456
  12. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  13. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  14. 2020Data Augmentation for Graph Neural Networkscited by 200
  15. 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
  16. 2019Batch Virtual Adversarial Training for Graph Convolutional Networkscited by 33
  17. 2020Self-supervised Training of Graph Convolutional Networkscited by 24

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 7; 2024: 10; 2025: 7.

30 papers.

Sort:

By area:

  1. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  2. 2023Structural Re-weighting Improves Graph Domain Adaptationcited by 45
  3. 2024Prompt Learning via Meta-Regularizationcited by 26
  4. 2022DAGAD: Data Augmentation for Graph Anomaly Detectioncited by 20
  5. 2023GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Expertscited by 19
  6. 2023Fused Gromov-Wasserstein Graph Mixup for Graph-level Classificationscited by 15
  7. 2022Data Augmentation on Graphs: A Technical Surveycited by 10
  8. 2024Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptationcited by 10
  9. 2024Cross-Domain Graph Data Scaling: A Showcase with Diffusion Modelscited by 8
  10. 2022FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classificationcited by 7
  11. 2025Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphscited by 5
  12. 2022Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networkscited by 4
18 more
  1. 2023Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphscited by 4
  2. 2024Node Duplication Improves Cold-start Link Predictioncited by 4
  3. 2024IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighborscited by 4
  4. 2024MLDGG: Meta-Learning for Domain Generalization on Graphscited by 4
  5. 2022Causally-guided Regularization of Graph Attention Improves Generalizabilitycited by 3
  6. 2024Graphs Generalization under Distribution Shiftscited by 3
  7. 2024DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networkscited by 3
  8. 2025GLAD: Generalizable Tuning for Vision-Language Modelscited by 3
  9. 2025Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environmentscited by 2
  10. 2023GEANN: Scalable Graph Augmentations for Multi-Horizon Time Series Forecastingcited by 1
  11. 2023FRGNN: Mitigating the Impact of Distribution Shift on Graph Neural Networks via Test-Time Feature Reconstructioncited by 1
  12. 2024Robust Traffic Forecasting against Spatial Shift over Yearscited by 1
  13. 2024Control the GNN: Utilizing Neural Controller with Lyapunov Stability for Test-Time Feature Reconstructioncited by 1
  14. 2025Graph Augmentation for Cross Graph Domain Generalizationcited by 1
  15. 2023SGA: A Graph Augmentation Method for Signed Graph Neural Networkscited by 0
  16. 2025CoATA: Effective Co-Augmentation of Topology and Attribute for Graph Neural Networkscited by 0
  17. 2025Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Krigingcited by 0
  18. 2025Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clusteringcited by 0