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

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.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• A Recurrent Latent Variable Model for Sequential Data
• Large-scale Multi-label Learning with Missing Labels
• Multi-Label Image Recognition with Graph Convolutional Networks
• End-to-End Learning for the Deep Multivariate Probit Model

Cited by in corpus (5)

• Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings
• Materials Representation and Transfer Learning for Multi-Property Prediction
• Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
• Evaluating Multi-label Classifiers with Noisy Labels
• Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators