2024/10/31 by Chenyu Wang, Sharut Gupta, Wang, Chenyu +11 · 4 citations
Computer Science · #Advanced Computational Techniques in Science and Engineering #Artificial Intelligence (cs.AI) #Computer science #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2410.23996
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/10/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Multimodal representation learning seeks to relate and decompose information inherent in multiple modalities. By disentangling modality-specific information from information that is shared across modalities, we can improve interpretability and robustness and enable downstream tasks such as the generation of counterfactual outcomes. Separating the two types of information is challenging since they are often deeply entangled in many real-world applications. We propose Disentangled Self-Supervised Learning (DisentangledSSL), a novel self-supervised approach for learning disentangled representations. We present a comprehensive analysis of the optimality of each disentangled representation, particularly focusing on the scenario not covered in prior work where the so-called Minimum Necessary Information (MNI) point is not attainable. We demonstrate that DisentangledSSL successfully learns shared and modality-specific features on multiple synthetic and real-world datasets and consistently outperforms baselines on various downstream tasks, including prediction tasks for vision-language data, as well as molecule-phenotype retrieval tasks for biological data. The code is available at https://github.com/uhlerlab/DisentangledSSL.