Understanding contrastive learning via distributionally robust optimization

J Wu, J Chen, J Wu, W Shi… - Advances in Neural …, 2024 - proceedings.neurips.cc
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (\eg labels). However, existing …
被引用次数：27 相关文章

Understanding Contrastive Learning via Distributionally Robust Optimization

J Wu, J Chen, J Wu, W Shi, X Wang, X He - arXiv preprint arXiv …, 2023 - arxiv.org
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (\eg labels). However, existing …

Understanding Contrastive Learning via Distributionally Robust Optimization

J Wu, J Chen, J Wu, W Shi, X Wang, X He - 2023 - junkangwu.github.io
Understanding Contrastive Learning via Distributionally Robust Optimization Page 1 1958
University of Science and Technology of China Understanding Contrastive Learning via …

Understanding contrastive learning via distributionally robust optimization

J Wu, J Chen, J Wu, W Shi, X Wang, X He - Proceedings of the 37th …, 2023 - dl.acm.org
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (eg, labels). However, existing …

Understanding Contrastive Learning via Distributionally Robust Optimization

J Wu, J Chen, J Wu, W Shi, X Wang, X He - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (\eg labels). However, existing …
[PDF] github.io

[PDF][PDF] Understanding Contrastive Learning via Distributionally Robust Optimization

JWJ Chen, JWWSX Wang, X He - jiawei-chen.github.io
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (eg, labels). However, existing …

Understanding Contrastive Learning via Distributionally Robust Optimization

J Wu, J Chen, J Wu, W Shi, X Wang, X He - Thirty-seventh Conference on … - openreview.net
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (\eg labels). However, existing …
[PDF] github.io

[PDF][PDF] Understanding Contrastive Learning via Distributionally Robust Optimization

JWJ Chen, JWWSX Wang, X He - hexiangnan.github.io
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (eg, labels). However, existing …
[PDF] github.io

[PDF][PDF] Understanding Contrastive Learning via Distributionally Robust Optimization

JWJ Chen, JWWSX Wang, X He - wujcan.github.io
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias,
wherein negative samples may encompass similar semantics (eg, labels). However, existing …