Rethinking Weak Supervision in Helping Contrastive Learning
This work addresses the problem of effectively utilizing weak supervision in contrastive learning for machine learning practitioners, providing theoretical insights but is incremental as it builds on existing contrastive learning paradigms.
The paper investigates whether noisy supervised information can directly aid contrastive learning without manual denoising, establishing a theoretical framework to compare semi-supervised and noisy labels. It proves that semi-supervised labels improve downstream classification error bounds, while noisy labels have limited effects.
Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noisy label learning. Despite the empirical evidence showing that semi-supervised labels improve the representations of contrastive learning, it remains unknown if noisy supervised information can be directly used in training instead of after manual denoising. Therefore, to explore the mechanical differences between semi-supervised and noisy-labeled information in helping contrastive learning, we establish a unified theoretical framework of contrastive learning under weak supervision. Specifically, we investigate the most intuitive paradigm of jointly training supervised and unsupervised contrastive losses. By translating the weakly supervised information into a similarity graph under the framework of spectral clustering based on the posterior probability of weak labels, we establish the downstream classification error bound. We prove that semi-supervised labels improve the downstream error bound whereas noisy labels have limited effects under such a paradigm. Our theoretical findings here provide new insights for the community to rethink the role of weak supervision in helping contrastive learning.