mlsanityData to 14 Oct 2026

Subgraph Generation for Generalizing on Out-of-Distribution Links

arXiv 2507.11710 ↗First posted 15 Jul 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graphs Neural Networks (GNNs) demonstrate high-performance on the link prediction (LP) task. However, these models often rely on all dataset samples being drawn from the same distribution. In addition, graph generative models (GGMs) show a pronounced ability to generate novel output graphs. Despite this, GGM applications remain largely limited to domain-specific tasks. To bridge this gap, we propose FLEX as a GGM framework which leverages two mechanism: (1) structurally-conditioned graph generation, and (2) adversarial co-training between an auto-encoder and GNN. As such, FLEX ensures structural-alignment between sample distributions to enhance link-prediction performance in out-of-distribution (OOD) scenarios. Notably, FLEX does not require expert knowledge to function in different OOD scenarios. Numerous experiments are conducted in synthetic and real-world OOD settings to demonstrate FLEX's performance-enhancing ability, with further analysis for understanding the effects of graph data augmentation on link structures. The source code is available here: https://github.com/revolins/FlexOOD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 61 references that are in the map. First posted on arXiv 15 Jul 2025.

Builds on

46 of 61 references.

References · 46

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  5. 2019Invariant Risk Minimizationcited by 1,854
  6. 2016Variational Graph Auto-Encoderscited by 1,382
  7. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  8. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  9. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  10. 2020In Search of Lost Domain Generalizationcited by 1,054
  11. 2018Link Prediction Based on Graph Neural Networkscited by 832
  12. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
34 more
  1. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  2. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  3. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
  4. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
  5. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 180
  6. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  7. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
  8. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
  9. 2022SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generatorscited by 99
  10. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 84
  11. 2023Autoregressive Diffusion Model for Graph Generationcited by 83
  12. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  13. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  14. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  15. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  16. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  17. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  18. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  19. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  20. 2018Semi-Implicit Variational Inferencecited by 55
  21. 2019Semi-Implicit Graph Variational Auto-Encoderscited by 54
  22. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  23. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  24. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  25. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  26. 2024Alleviating Structural Distribution Shift in Graph Anomaly Detectioncited by 32
  27. 2024Graph Out-of-Distribution Generalization via Causal Interventioncited by 31
  28. 2023On Generalized Degree Fairness in Graph Neural Networkscited by 28
  29. 2023SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generationcited by 28
  30. 2022Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysiscited by 18
  31. 2023LPFormer: An Adaptive Graph Transformer for Link Predictioncited by 17
  32. 2021Edge Proposal Sets for Link Predictioncited by 16
  33. 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
  34. 2023Meta OOD Learning for Continuously Adaptive OOD Detectioncited by 10

Built on by

Not cited yet.