mlsanityData to 7 Oct 2026

Empowering Graph Representation Learning with Test-Time Graph Transformation

arXiv 2210.03561 ↗First posted 7 Oct 2022cs.LG cs.AI stat.MLcited by 66

Not on the map. Why?

Abstract (arXiv)

As powerful tools for representation learning on graphs, graph neural networks (GNNs) have facilitated various applications from drug discovery to recommender systems. Nevertheless, the effectiveness of GNNs is immensely challenged by issues related to data quality, such as distribution shift, abnormal features and adversarial attacks. Recent efforts have been made on tackling these issues from a modeling perspective which requires additional cost of changing model architectures or re-training model parameters. In this work, we provide a data-centric view to tackle these issues and propose a graph transformation framework named GTrans which adapts and refines graph data at test time to achieve better performance. We provide theoretical analysis on the design of the framework and discuss why adapting graph data works better than adapting the model. Extensive experiments have demonstrated the effectiveness of GTrans on three distinct scenarios for eight benchmark datasets where suboptimal data is presented. Remarkably, GTrans performs the best in most cases with improvements up to 2.8%, 8.2% and 3.8% over the best baselines on three experimental settings. Code is released at https://github.com/ChandlerBang/GTrans.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Builds on 63 of its 87 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

63 of 87 references.

References · 63

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  9. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  10. 2018Deep Graph Infomaxcited by 1,101
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  12. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
38 more
  1. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  3. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  4. 2019Graph Neural Networks for Social Recommendationcited by 711
  5. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  6. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  7. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  8. 2019Multi-scale Attributed Node Embeddingcited by 543
  9. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  10. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  11. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  12. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  13. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  14. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  15. 2021Graph Self-Supervised Learning: A Surveycited by 289
  16. 2021Graph Contrastive Learning Automatedcited by 287
  17. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  18. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  19. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  20. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  21. 2020Data Augmentation for Graph Neural Networkscited by 200
  22. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  23. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  24. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  25. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  26. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  27. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  28. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  29. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  30. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  31. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  32. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  33. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  34. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  35. 2021Robustness of Graph Neural Networks at Scalecited by 100
  36. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  37. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  38. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 27; 2025: 15; 2026: 14.

66 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  3. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  4. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  5. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  6. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  7. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 29
  8. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  9. 2024Pairwise Alignment Improves Graph Domain Adaptationcited by 25
  10. 2023Data-centric Graph Learning: A Surveycited by 22
  11. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  12. 2023GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Expertscited by 19
38 more
  1. 2024A Survey of Data-Efficient Graph Learningcited by 18
  2. 2024GOODAT: Towards Test-time Graph Out-of-Distribution Detectioncited by 17
  3. 2024Subgraph Pooling: Tackling Negative Transfer on Graphscited by 17
  4. 2024Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learningcited by 17
  5. 2025Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesicscited by 17
  6. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  7. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  8. 2024Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptationcited by 15
  9. 2024Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspectivecited by 13
  10. 2024How Interpretable Are Interpretable Graph Neural Networks?cited by 13
  11. 2024Online GNN Evaluation Under Test-time Graph Distribution Shiftscited by 12
  12. 2025Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Timecited by 12
  13. 2024Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptationcited by 10
  14. 2024Can Modifying Data Address Graph Domain Adaptation?cited by 9
  15. 2026USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptationcited by 9
  16. 2025GCAL: Adapting Graph Models to Evolving Domain Shiftscited by 8
  17. 2024Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphscited by 6
  18. 2024Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and Morecited by 6
  19. 2024Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networkscited by 6
  20. 2024Promoting Fairness in Link Prediction with Graph Enhancementcited by 6
  21. 2023CARL-G: Clustering-Accelerated Representation Learning on Graphscited by 5
  22. 2024How Does Message Passing Improve Collaborative Filtering?cited by 5
  23. 2024Dissecting the Failure of Invariant Learning on Graphscited by 5
  24. 2023Spectral-Aware Augmentation for Enhanced Graph Representation Learningcited by 4
  25. 2025Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptationcited by 4
  26. 2025Geometric Algorithms for Neural Combinatorial Optimization with Constraintscited by 4
  27. 2024Test-Time Training on Graphs with Large Language Models (LLMs)cited by 3
  28. 2025Graph Defense Diffusion Modelcited by 3
  29. 2025Structural Alignment Improves Graph Test-Time Adaptationcited by 2
  30. 2023FRGNN: Mitigating the Impact of Distribution Shift on Graph Neural Networks via Test-Time Feature Reconstructioncited by 1
  31. 2024Control the GNN: Utilizing Neural Controller with Lyapunov Stability for Test-Time Feature Reconstructioncited by 1
  32. 2025Cross-Domain Graph Anomaly Detection via Test-Time Training with Homophily-Guided Self-Supervisioncited by 1
  33. 2025Shapley-Guided Utility Learning for Effective Graph Inference Data Valuationcited by 1
  34. 2025Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogrammingcited by 1
  35. 2025Does Homophily Help in Robust Test-time Node Classification?cited by 1
  36. 2026From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detectioncited by 1
  37. 2026GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuningcited by 1
  38. 2026PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphscited by 1

50 most cited of 66 All 66 (JSON)