paper-with-me

Papers

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

2023-04-30 · NeurIPS 2023 11 · Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama, Mohan Kankanhalli

Adversarial contrastive learning (ACL) is a technique that enhances standard contrastive learning (SCL) by incorporating adversarial data to learn a robust representation that can withstand adversarial attacks and common corruptions without requiring costly annotations. To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation. However, it is unclear how the style-independence property benefits ACL-learned robust representations. In this paper, we leverage the technique of causal reasoning to interpret the ACL and propose adversarial invariant regularization (AIR) to enforce independence from style factors. We regulate the ACL using both SIR and AIR to output the robust representation. Theoretically, we show that AIR implicitly encourages the representational distance between different views of natural data and their adversarial variants to be independent of style factors. Empirically, our experimental results show that invariant regularization significantly improves the performance of state-of-the-art ACL methods in terms of both standard generalization and robustness on downstream tasks. To the best of our knowledge, we are the first to apply causal reasoning to interpret ACL and develop AIR for enhancing ACL-learned robust representations. Our source code is at https://github.com/GodXuxilie/Enhancing_ACL_via_AIR.

📄 PDF Abstract BibTeX arXiv:2305.00374

Code (1)

godxuxilie/enhancing_acl_via_air 공식 구현 pytorch

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

RegMix: Adversarial Mutual and Generalization Regularization for Enhancing DNN Robustness

2025-10-06 · Zhenyu Liu, Varun Ojha arxiv

Adversarial training is the most effective defense against adversarial attacks. The effectiveness of the adversarial attacks has been on the design of its loss function and regularization term. The most widely used loss …

Knowledge DistillationAdversarial Robustness

Contrastive Adversarial Training for Unsupervised Domain Adaptation

2024-07-17 · Jiahong Chen, Zhilin Zhang, Lucy Li, Behzad Shahrasbi 외

Domain adversarial training has shown its effective capability for finding domain invariant feature representations and been successfully adopted for various domain adaptation tasks. However, recent advances of large mod…

Domain AdaptationUnsupervised Domain Adaptation

A Study on Adversarial Robustness of Discriminative Prototypical Learning

2025-04-03 · Ramin Zarei Sabzevar, Hamed Mohammadzadeh, Tahmineh Tavakoli, Ahad Harati

Deep neural networks demonstrate significant vulnerability to adversarial perturbations, posing risks for critical applications. Current adversarial training methods predominantly focus on robustness against attacks with…

Adversarial Robustness

Enhancing Adversarial Transferability via Information Bottleneck Constraints

2024-06-08 · Biqing Qi, Junqi Gao, Jianxing Liu, Ligang Wu 외

From the perspective of information bottleneck (IB) theory, we propose a novel framework for performing black-box transferable adversarial attacks named IBTA, which leverages advancements in invariant features. Intuitive…

Adversarial Transformations for Semi-Supervised Learning

2019-11-13 · Teppei Suzuki, Ikuro Sato

We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning. RAT is designed to enhance robustness of the output distribution of class prediction for a given data against…

General Classificationimage-classificationImage ClassificationSemi-Supervised Image Classification