paper-with-me

홈 › Papers

Robustness of Unsupervised Representation Learning without Labels

2022-10-08 · Aleksandar Petrov, Marta Kwiatkowska

Unsupervised representation learning leverages large unlabeled datasets and is competitive with supervised learning. But non-robust encoders may affect downstream task robustness. Recently, robust representation encoders have become of interest. Still, all prior work evaluates robustness using a downstream classification task. Instead, we propose a family of unsupervised robustness measures, which are model- and task-agnostic and label-free. We benchmark state-of-the-art representation encoders and show that none dominates the rest. We offer unsupervised extensions to the FGSM and PGD attacks. When used in adversarial training, they improve most unsupervised robustness measures, including certified robustness. We validate our results against a linear probe and show that, for MOCOv2, adversarial training results in 3 times higher certified accuracy, a 2-fold decrease in impersonation attack success rate and considerable improvements in certified robustness.

📄 PDF Abstract BibTeX arXiv:2210.04076

Code (1)

aleksandarpetrov/unsupervised-robustness 공식 구현 pytorch

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation

2022-01-20 · Sixiao Zhang, Hongxu Chen, Xiangguo Sun, Yicong Li 외

Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive l…

Adversarial AttackContrastive LearningGraph Representation LearningLink Prediction+2

Unsupervised Adversarially-Robust Representation Learning on Graphs

2020-12-04 · Jiarong Xu, Yang Yang, Junru Chen, Chunping Wang 외

Unsupervised/self-supervised pre-training methods for graph representation learning have recently attracted increasing research interests, and they are shown to be able to generalize to various downstream applications. Y…

Adversarial RobustnessCommunity DetectionGraph LearningGraph Representation Learning+3

Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs

2026-04-08 · Tunazzina Islam arxiv

Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate with…

Representation LearningTopic Models

Unsupervised Robust Domain Adaptation without Source Data

2021-03-26 · Peshal Agarwal, Danda Pani Paudel, Jan-Nico Zaech, Luc van Gool

We study the problem of robust domain adaptation in the context of unavailable target labels and source data. The considered robustness is against adversarial perturbations. This paper aims at answering the question of f…

Domain Adaptationimage-classificationImage ClassificationUnsupervised Domain Adaptation

Transferable Unsupervised Robust Representation Learning

2021-01-01 · De-An Huang, Zhiding Yu, Anima Anandkumar

Robustness is an important, and yet, under-explored aspect of unsupervised representation learning, which has seen a lot of recent developments. In this work, we address this gap by developing a novel framework: Unsuperv…

Data AugmentationRepresentation LearningTransfer Learning