论文标题
对抗性对比学习，通过置换集群作业
Adversarial Contrastive Learning by Permuting Cluster Assignments
论文作者
论文摘要
对比学习已成为一种有效的自我监督的表示技术，广受欢迎。几个研究方向改善了传统的对比方法，例如，原型对比度方法可以通过考虑集群原型或群集分配来更好地捕获实例之间的语义相似性，并减轻计算负担，而对抗性实例的对比度方法可以改善对各种攻击的鲁棒性。据我们所知，没有先前的工作共同考虑鲁棒性，群集的语义相似性和计算效率。在这项工作中，我们提出了Swaro，这是一个对抗性对比框架，该框架结合了集群分配排列以生成代表性的对抗样本。我们在多个基准数据集上评估了Swaro，并对各种白色框和黑盒攻击进行了评估，从而对最先进的基线进行了一致的改进。
Contrastive learning has gained popularity as an effective self-supervised representation learning technique. Several research directions improve traditional contrastive approaches, e.g., prototypical contrastive methods better capture the semantic similarity among instances and reduce the computational burden by considering cluster prototypes or cluster assignments, while adversarial instance-wise contrastive methods improve robustness against a variety of attacks. To the best of our knowledge, no prior work jointly considers robustness, cluster-wise semantic similarity and computational efficiency. In this work, we propose SwARo, an adversarial contrastive framework that incorporates cluster assignment permutations to generate representative adversarial samples. We evaluate SwARo on multiple benchmark datasets and against various white-box and black-box attacks, obtaining consistent improvements over state-of-the-art baselines.
