mlsanityData to 14 Oct 2026

Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection

arXiv 2302.03857 ↗First posted 8 Feb 2023cs.LG cs.CRcited by 14

Not on the map. Why?

Abstract (arXiv)

Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks. However, ACL needs tremendous running time to generate the adversarial variants of all training data, which limits its scalability to large datasets. To speed up ACL, this paper proposes a robustness-aware coreset selection (RCS) method. RCS does not require label information and searches for an informative subset that minimizes a representational divergence, which is the distance of the representation between natural data and their virtual adversarial variants. The vanilla solution of RCS via traversing all possible subsets is computationally prohibitive. Therefore, we theoretically transform RCS into a surrogate problem of submodular maximization, of which the greedy search is an efficient solution with an optimality guarantee for the original problem. Empirically, our comprehensive results corroborate that RCS can speed up ACL by a large margin without significantly hurting the robustness transferability. Notably, to the best of our knowledge, we are the first to conduct ACL efficiently on the large-scale ImageNet-1K dataset to obtain an effective robust representation via RCS. Our source code is at https://github.com/GodXuxilie/Efficient_ACL_via_RCS.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 49 of its 77 references that are in the map. First posted on arXiv 8 Feb 2023.

Builds on

49 of 77 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  10. 2016Wide Residual Networkscited by 3,070
  11. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  12. 2016Adversarial examples in the physical worldcited by 1,769
37 more
  1. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  2. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  4. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  5. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  6. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  7. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  8. 2019Adversarial Training for Free!cited by 643
  9. 2021ImageNet-21K Pretraining for the Massescited by 613
  10. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 425
  11. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  12. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  13. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  14. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 316
  15. 2019Adversarial Examples Improve Image Recognitioncited by 286
  16. 2021GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Trainingcited by 274
  17. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  18. 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 226
  19. 2020Understanding and Improving Fast Adversarial Trainingcited by 214
  20. 2020Representation Learning via Invariant Causal Mechanismscited by 199
  21. 2019Are Labels Required for Improving Adversarial Robustness?cited by 163
  22. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  23. 2020Adversarial Self-Supervised Contrastive Learningcited by 139
  24. 2018Invariance, Causality and Robustnesscited by 123
  25. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  26. 2020Contrastive Learning with Adversarial Examplescited by 91
  27. 2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 77
  28. 2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 76
  29. 2021RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learningcited by 74
  30. 2020What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentationcited by 50
  31. 2022Efficient and Effective Augmentation Strategy for Adversarial Trainingcited by 43
  32. 2022Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustnesscited by 20
  33. 2022Adversarial Contrastive Learning via Asymmetric InfoNCEcited by 13
  34. 2022Adversarial Coreset Selection for Efficient Robust Trainingcited by 9
  35. 2022Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularizationcited by 8
  36. 2020Weakly Submodular Function Maximization Using Local Submodularity Ratiocited by 7
  37. 2018Non-submodular Function Maximization subject to a Matroid Constraint, with Applicationscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 4; 2025: 6.

14 papers.

Sort:

By area:

  1. 2024Few-Shot Adversarial Prompt Learning on Vision-Language Modelscited by 39
  2. 2023Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruningcited by 38
  3. 2024Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustmentcited by 33
  4. 2025Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metricscited by 12
  5. 2023Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularizationcited by 10
  6. 2023AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Frameworkcited by 9
  7. 2024AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuningcited by 7
  8. 2025Training-Free Dataset Pruning for Instance Segmentationcited by 7
  9. 2025FedSC: Federated Learning with Semantic-Aware Collaborationcited by 3
  10. 2024Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolationcited by 2
  11. 2025Adversarial Robustness of Discriminative Self-Supervised Learning in Visioncited by 1
  12. 2025How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reductioncited by 1
2 more
  1. 2023Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteriacited by 0
  2. 2025Pay More Attention to the Robustness of Prompt for Instruction Data Miningcited by 0