Factorized Contrastive Learning: Going Beyond Multi-view Redundancy
Abstract
In a wide range of multimodal tasks, contrastive learning has become a particularly appealing approach since it can successfully learn representations from abundant unlabeled data with only pairing information (e.g., image-caption or video-audio pairs). Underpinning these approaches is the assumption of multi-view redundancy - that shared information between modalities is necessary and sufficient for downstream tasks. However, in many real-world settings, task-relevant information is also contained in modality-unique regions: information that is only present in one modality but still relevant to the task. How can we learn self-supervised multimodal representations to capture both shared and unique information relevant to downstream tasks? This paper proposes FactorCL, a new multimodal representation learning method to go beyond multi-view redundancy. FactorCL is built from three new contributions: (1) factorizing task-relevant information into shared and unique representations, (2) capturing task-relevant information via maximizing MI lower bounds and removing task-irrelevant information via minimizing MI upper bounds, and (3) multimodal data augmentations to approximate task relevance without labels. On large-scale real-world datasets, FactorCL captures both shared and unique information and achieves state-of-the-art results on six benchmarks
Cite
@article{arxiv.2306.05268,
title = {Factorized Contrastive Learning: Going Beyond Multi-view Redundancy},
author = {Paul Pu Liang and Zihao Deng and Martin Ma and James Zou and Louis-Philippe Morency and Ruslan Salakhutdinov},
journal= {arXiv preprint arXiv:2306.05268},
year = {2023}
}
Comments
NeurIPS 2023. Code available at: https://github.com/pliang279/FactorCL