mlsanityData to 7 Oct 2026

Test-Time Training for Graph Neural Networks

arXiv 2210.08813 ↗First posted 17 Oct 2022cs.LG cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have made tremendous progress in the graph classification task. However, a performance gap between the training set and the test set has often been noticed. To bridge such gap, in this work we introduce the first test-time training framework for GNNs to enhance the model generalization capacity for the graph classification task. In particular, we design a novel test-time training strategy with self-supervised learning to adjust the GNN model for each test graph sample. Experiments on the benchmark datasets have demonstrated the effectiveness of the proposed framework, especially when there are distribution shifts between training set and test set. We have also conducted exploratory studies and theoretical analysis to gain deeper understandings on the rationality of the design of the proposed graph test time training framework (GT3).

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

39 of 50 references.

References · 39

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2016Variational Graph Auto-Encoderscited by 1,373
  11. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  12. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
27 more
  1. 2018Deep Graph Infomaxcited by 1,101
  2. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  3. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  4. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  5. 2019Graph Neural Networks for Social Recommendationcited by 711
  6. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  7. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  8. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  9. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  10. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  11. 2020Understanding the Failure Modes of Out-of-Distribution Generalizationcited by 146
  12. 2020Self-Supervised Policy Adaptation during Deploymentcited by 121
  13. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  14. 2019Graph Convolutional Networks with EigenPoolingcited by 94
  15. 2020Scalable Graph Neural Networks via Bidirectional Propagationcited by 87
  16. 2019Graph Transformer for Graph-to-Sequence Learningcited by 82
  17. 2021Elastic Graph Neural Networkscited by 67
  18. 2021MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaptioncited by 65
  19. 2019Text Level Graph Neural Network for Text Classificationcited by 60
  20. 2019Test-Time Training with Self-Supervision for Generalization under Distribution Shiftscited by 55
  21. 2021AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Searchcited by 38
  22. 2019Deep Representation Learning for Social Network Analysiscited by 35
  23. 2022HousE: Knowledge Graph Embedding with Householder Parameterizationcited by 29
  24. 2021Learning to Track Instances without Video Annotationscited by 18
  25. 2022Graph Neural Networks for Multimodal Single-Cell Data Integrationcited by 18
  26. 2022Going Deeper into Permutation-Sensitive Graph Neural Networkscited by 15
  27. 2021Localized Graph Collaborative Filteringcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 3; 2026: 3.

17 papers.

Sort:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2023CONVERT:Contrastive Graph Clustering with Reliable Augmentationcited by 23
  3. 2024A Survey of Data-Efficient Graph Learningcited by 18
  4. 2024Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learningcited by 17
  5. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  6. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  7. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  8. 2024Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptationcited by 10
  9. 2024Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphscited by 6
  10. 2023Addressing the Impact of Localized Training Data in Graph Neural Networkscited by 2
  11. 2025Structural Alignment Improves Graph Test-Time Adaptationcited by 2
  12. 2025Cross-Domain Graph Anomaly Detection via Test-Time Training with Homophily-Guided Self-Supervisioncited by 1
5 more
  1. 2026GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuningcited by 1
  2. 2026PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphscited by 1
  3. 2024One-Step Late Fusion Multi-view Clustering with Compressed Subspacecited by 0
  4. 2025Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmarkcited by 0
  5. 2026When does distribution shift break graph neural networks calibration?cited by 0