paper-with-me

Papers

Robust Contrastive Learning With Theory Guarantee

2023-11-16 · Ngoc N. Tran, Lam Tran, Hoang Phan, Anh Bui, Tung Pham, Toan Tran, Dinh Phung, Trung Le

Contrastive learning (CL) is a self-supervised training paradigm that allows us to extract meaningful features without any label information. A typical CL framework is divided into two phases, where it first tries to learn the features from unlabelled data, and then uses those features to train a linear classifier with the labeled data. While a fair amount of existing theoretical works have analyzed how the unsupervised loss in the first phase can support the supervised loss in the second phase, none has examined the connection between the unsupervised loss and the robust supervised loss, which can shed light on how to construct an effective unsupervised loss for the first phase of CL. To fill this gap, our work develops rigorous theories to dissect and identify which components in the unsupervised loss can help improve the robust supervised loss and conduct proper experiments to verify our findings.

📄 PDF Abstract BibTeX arXiv:2311.09671

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

Chaos is a Ladder: A New Understanding of Contrastive Learning

2021-09-29 · ICLR 2022 4 · Yifei Wang, Qi Zhang, Yisen Wang, Jiansheng Yang 외

Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee…

Contrastive LearningSelf-Supervised Learning

Convergence of energy-based learning in linear resistive networks

2025-03-01 · Anne-Men Huijzer, Thomas Chaffey, Bart Besselink, Henk J. van Waarde

Energy-based learning algorithms are alternatives to backpropagation and are well-suited to distributed implementations in analog electronic devices. However, a rigorous theory of convergence is lacking. We make a first …

Contrastive Learning

Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

2022-03-25 · Yifei Wang, Qi Zhang, Yisen Wang, Jiansheng Yang 외

Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee…

ARCContrastive LearningModel SelectionSelf-Supervised Learning

Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis

2023-04-01 · Hiroki Waida, Yuichiro Wada, Léo Andéol, Takumi Nakagawa 외

Contrastive learning is an efficient approach to self-supervised representation learning. Although recent studies have made progress in the theoretical understanding of contrastive learning, the investigation of how to c…

Contrastive LearningRepresentation Learning

A Statistical Theory of Contrastive Pre-training and Multimodal Generative AI

2025-01-08 · Kazusato Oko, Licong Lin, Yuhang Cai, Song Mei

Multi-modal generative AI systems, such as those combining vision and language, rely on contrastive pre-training to learn representations across different modalities. While their practical benefits are widely acknowledge…

zero-shot-classificationZero-Shot Learning