Identifiability Results for Multimodal Contrastive Learning
Contrastive learning is a cornerstone underlying recent progress in multi-view and multimodal learning, e.g., in representation learning with image/caption pairs. While its effectiveness is not yet fully understood, a line of recent work reveals that contrastive learning can invert the data generating process and recover ground truth latent factors shared between views. In this work, we present new identifiability results for multimodal contrastive learning, showing that it is possible to recover shared factors in a more general setup than the multi-view setting studied previously. Specifically, we distinguish between the multi-view setting with one generative mechanism (e.g., multiple cameras of the same type) and the multimodal setting that is characterized by distinct mechanisms (e.g., cameras and microphones). Our work generalizes previous identifiability results by redefining the generative process in terms of distinct mechanisms with modality-specific latent variables. We prove that contrastive learning can block-identify latent factors shared between modalities, even when there are nontrivial dependencies between factors. We empirically verify our identifiability results with numerical simulations and corroborate our findings on a complex multimodal dataset of image/text pairs. Zooming out, our work provides a theoretical basis for multimodal representation learning and explains in which settings multimodal contrastive learning can be effective in practice.
Code (1)
Tasks
Contrastive LearningRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hierarchical Contrastive Learning for Multimodal Data
Multimodal representation learning is commonly built on a shared-private decomposition, treating latent information as either common to all modalities or specific to one. This binary view is often inadequate: many factor…
Representation LearningContrastive LearningBeyond DAGs: A Latent Partial Causal Model for Multimodal Learning
Directed acyclic graphs (DAGs) are fundamental graph structures in causal modeling, but identifying the desired DAG from observational data often requires strong assumptions that may not hold in real-world scenarios, esp…
Contrastive LearningDisentanglementDomain GeneralizationFew-Shot Learning+1Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
Causal representation learning (CRL) seeks to uncover meaningful latent variables and their corresponding causal structure from high-dimensional observational data. Although its significance, CRL identifiability remains …
Representation LearningOn Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
Nonlinear independent component analysis (nICA) aims at recovering statistically independent latent components that are mixed by unknown nonlinear functions. Central to nICA is the identifiability of the latent component…
Contrastive LearningDisentanglementRepresentation LearningSelf-Supervised LearningIdentifiable Contrastive Learning with Automatic Feature Importance Discovery
Existing contrastive learning methods rely on pairwise sample contrast $z_x^\top z_{x'}$ to learn data representations, but the learned features often lack clear interpretability from a human perspective. Theoretically, …