Hierarchical Contrastive Learning for Multimodal Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Huichao, Yu, Junhan, Zhou, Doudou
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915920104914944
author Li, Huichao
Yu, Junhan
Zhou, Doudou
author_facet Li, Huichao
Yu, Junhan
Zhou, Doudou
contents 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 factors are shared by only subsets of modalities, and ignoring such partial sharing can over-align unrelated signals and obscure complementary information. We propose Hierarchical Contrastive Learning (HCL), a framework that learns globally shared, partially shared, and modality-specific representations within a unified model. HCL combines a hierarchical latent-variable formulation with structural sparsity and a structure-aware contrastive objective that aligns only modalities that genuinely share a latent factor. Under uncorrelated latent variables, we prove identifiability of the hierarchical decomposition, establish recovery guarantees for the loading matrices, and derive parameter estimation and excess-risk bounds for downstream prediction. Simulations show accurate recovery of hierarchical structure and effective selection of task-relevant components. On multimodal electronic health records, HCL yields more informative representations and consistently improves predictive performance.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05462
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchical Contrastive Learning for Multimodal Data
Li, Huichao
Yu, Junhan
Zhou, Doudou
Machine Learning
Statistics Theory
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 factors are shared by only subsets of modalities, and ignoring such partial sharing can over-align unrelated signals and obscure complementary information. We propose Hierarchical Contrastive Learning (HCL), a framework that learns globally shared, partially shared, and modality-specific representations within a unified model. HCL combines a hierarchical latent-variable formulation with structural sparsity and a structure-aware contrastive objective that aligns only modalities that genuinely share a latent factor. Under uncorrelated latent variables, we prove identifiability of the hierarchical decomposition, establish recovery guarantees for the loading matrices, and derive parameter estimation and excess-risk bounds for downstream prediction. Simulations show accurate recovery of hierarchical structure and effective selection of task-relevant components. On multimodal electronic health records, HCL yields more informative representations and consistently improves predictive performance.
title Hierarchical Contrastive Learning for Multimodal Data
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2604.05462