Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model

TL;DR

This paper introduces MPVAE, a novel multi-label classification framework that learns disentangled embeddings and models label correlations with a covariance-aware multivariate probit approach, improving accuracy and robustness.

Contribution

The paper presents MPVAE, a new model that effectively learns label and feature embeddings and captures label correlations through a shared covariance matrix, advancing multi-label classification.

Findings

MPVAE outperforms state-of-the-art methods on multiple datasets.

MPVAE remains robust under noisy conditions.

The learned covariance matrix provides interpretable insights.

Abstract

Multi-label classification is the challenging task of predicting the presence and absence of multiple targets, involving representation learning and label correlation modeling. We propose a novel framework for multi-label classification, Multivariate Probit Variational AutoEncoder (MPVAE), that effectively learns latent embedding spaces as well as label correlations. MPVAE learns and aligns two probabilistic embedding spaces for labels and features respectively. The decoder of MPVAE takes in the samples from the embedding spaces and models the joint distribution of output targets under a Multivariate Probit model by learning a shared covariance matrix. We show that MPVAE outperforms the existing state-of-the-art methods on a variety of application domains, using public real-world datasets. MPVAE is further shown to remain robust under noisy settings. Lastly, we demonstrate the interpretability of the learned covariance by a case study on a bird observation dataset.