paper-with-me

홈 › Papers

Do More Negative Samples Necessarily Hurt in Contrastive Learning?

2022-05-03 · Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath

Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more "negative samples" in the contrastive loss improves downstream classification performance initially, beyond a threshold, it hurts downstream performance due to a "collision-coverage" trade-off. But is such a phenomenon inherent in contrastive learning? We show in a simple theoretical setting, where positive pairs are generated by sampling from the underlying latent class (introduced by Saunshi et al. (ICML 2019)), that the downstream performance of the representation optimizing the (population) contrastive loss in fact does not degrade with the number of negative samples. Along the way, we give a structural characterization of the optimal representation in our framework, for noise contrastive estimation. We also provide empirical support for our theoretical results on CIFAR-10 and CIFAR-100 datasets.

📄 PDF Abstract BibTeX arXiv:2205.01789

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

Contrast Is All You Need

2023-07-06 · Burak Kilic, Florix Bex, Albert Gatt

In this study, we analyze data-scarce classification scenarios, where available labeled legal data is small and imbalanced, potentially hurting the quality of the results. We focused on two finetuning objectives; SetFit …

AllClassificationContrastive LearningSentence

Synthetic Hard Negative Samples for Contrastive Learning

2023-04-06 · Hengkui Dong, Xianzhong Long, Yun Li, Lei Chen

Contrastive learning has emerged as an essential approach for self-supervised learning in visual representation learning. The central objective of contrastive learning is to maximize the similarities between two augmente…

Contrastive LearningRepresentation LearningSelf-Supervised Learning

ConCur: Self-supervised graph representation based on contrastive learning with curriculum negative sampling

2023-09-01 · journal 2023 9 · Rong Yan, Peng Bao

Contrastive learning has made breakthrough advancements in graph representation learning, which encourages the representation of positive samples to be close and those of negative samples to be far away. However, existin…

Contrastive LearningGraph Representation LearningNode ClassificationRepresentation Learning+1

Debiased Contrastive Learning of Unsupervised Sentence Representations

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recently, contrastive learning has shown effectiveness in fine-tuning pre-trained language models (PLM) to derive sentence representations, which pulls augmented positive examples together to improve the alignment while …

Contrastive LearningSemantic Textual SimilaritySentence

Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samples

2023-11-01 · Hengkui Dong, Xianzhong Long, Yun Li

Contrastive learning predicts whether two images belong to the same category by training a model to make their feature representations as close or as far away as possible. In this paper, we rethink how to mine samples in…

Contrastive LearningData Augmentation