mlsanityData to 7 Oct 2026

Bridging OOD Detection and Generalization: A Graph-Theoretic View

arXiv 2409.18205 ↗First posted 26 Sep 2024cs.LG stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

In the context of modern machine learning, models deployed in real-world scenarios often encounter diverse data shifts like covariate and semantic shifts, leading to challenges in both out-of-distribution (OOD) generalization and detection. Despite considerable attention to these issues separately, a unified framework for theoretical understanding and practical usage is lacking. To bridge the gap, we introduce a graph-theoretic framework to jointly tackle both OOD generalization and detection problems. By leveraging the graph formulation, data representations are obtained through the factorization of the graph's adjacency matrix, enabling us to derive provable error quantifying OOD generalization and detection performance. Empirical results showcase competitive performance in comparison to existing methods, thereby validating our theoretical underpinnings. Code is publicly available at https://github.com/deeplearning-wisc/graph-spectral-ood.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 85 of its 116 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

85 of 116 references.

References · 85

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  5. 2016Wide Residual Networkscited by 3,057
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  10. 2013Describing Textures in the Wildcited by 2,110
  11. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  12. 2019Invariant Risk Minimizationcited by 1,832
38 more
  1. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  3. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  4. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  8. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  9. 2020In Search of Lost Domain Generalizationcited by 1,042
  10. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  12. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  13. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  14. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  15. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  16. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  17. 2021Domain Generalization with MixStylecited by 563
  18. 2015Towards Open Set Deep Networkscited by 533
  19. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  20. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  21. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  22. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  23. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  24. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  25. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  26. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 311
  27. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  28. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  29. 2021Gradient Matching for Domain Generalizationcited by 258
  30. 2019Episodic Training for Domain Generalizationcited by 245
  31. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  32. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  33. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  34. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  35. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  36. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  37. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  38. 2021Open-World Semi-Supervised Learningcited by 165

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRIcited by 12
  2. 2025Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learningcited by 11
  3. 2026Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detectioncited by 1