stat.MLNov 15, 2026

Integrating Latent Block Models into Variational Autoencoders for Disentangled Representation Learning

Authors: Anasse Essalih, Reda Khoufache, Laurent Durville, Mohamed-Cherif Rahal, Mustapha Lebbah, Hanene Azzag, Walid Kheriji, Fouad Hadj Selem

Organizations: VEDECOM Institute · DAVID Lab, UVSQ, Paris-Saclay University · TSM Unit UVSQ, Paris-Saclay University · DAVID Lab UVSQ, Paris-Saclay University · 

Abstract

We introduce LBM-VAE, a novel framework that integrates Latent Block Models (LBMs) into Variational Autoencoders (VAEs) to jointly cluster observations and latent dimensions. Beyond its clustering capabilities, LBM-VAE provides a block-structured latent representation that naturally supports disentangled representation learning. In contrast to conventional approaches that associate each factor of variation with an individual latent dimension, our framework allows factors of variation to be encoded across groups of latent dimensions. Experimental results demonstrate the promising clustering performance of LBM-VAE, while achieving competitive results in disentangled representation learning. LBM-VAE highlights the potential of combining co-clustering and variational inference to learn structured and interpretable latent representations.

Figures & tables

Explore similar work

CardsList
  1. A Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation

    Mar 11, 2026Xiaoan Lang, Md Mostafizer Rahman, Fang LiuVariational AutoencodersDisentangled Representation Learning

  2. Sculpting the Latent Space: Disentanglement with WAE-MMD and Programmable Priors

    Oct 13, 2025Quentin Fruytier, Akshay Malhotra, Shahab Hamidi-Rad +3Disentangled Representation LearningSemantic Representation Learning