HCL learns hierarchical multimodal representations via latent variables, structural sparsity, and structure-aware contrastive loss, with identifiability proofs under uncorrelated latents and improved performance on EHR data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hierarchical Contrastive Learning for Multimodal Data
HCL learns hierarchical multimodal representations via latent variables, structural sparsity, and structure-aware contrastive loss, with identifiability proofs under uncorrelated latents and improved performance on EHR data.