ProSampler: Improving Contrastive Learning by Better Mini-batch Sampling

Zhen Yang, Tinglin Huang, Ming Ding, Zhitao Ying, Yukuo Cen, Yangliao Geng, Yuxiao Dong, Jie Tang

Keywords: global hard negative sampling, contrastive learning

Abstract: In-batch contrastive learning has emerged as a state-of-the-art self-supervised learning solution, with the philosophy of bringing semantically similar instances closer while pushing dissimilar instances apart within a mini-batch. However, the in-batch negative sharing strategy is limited by the batch size and falls short of prioritizing the informative negatives (i.e., hard negatives) globally. In this paper, we propose to sample mini-batches with hard negatives on a proximity graph in which the instances (nodes) are connected according to the similarity measurement. Sampling on the proximity graph can better exploit the hard negatives globally by bridging in similar instances from the entire dataset. The proposed method can flexibly explore the negatives by modulating two parameters, and we show that such flexibility is the key to better exploit hard negative globally. We evaluate the proposed method on three representative contrastive learning algorithms, each of which corresponds to one modality: image, text, and graph. Besides, we also apply it to the variants of the InfoNCE objective to verify its generality. The results show that our method can consistently boost the performance of contrastive methods, with a relative improvement of 2.5% for SimCLR on ImageNet-100, 1.4% for SimCSE on the standard STS task, and 1.2% for GraphCL on the COLLAB dataset.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning