Learning Deep Latent Spaces for Multi-Label Classification

TL;DR

This paper introduces C2AE, a deep neural network model that learns joint feature-label embeddings and exploits label dependencies to improve multi-label classification accuracy, even with missing labels.

Contribution

The paper presents a novel deep latent space model combining canonical correlation analysis and autoencoders for enhanced multi-label classification, including handling missing labels.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Effectively models label dependencies and handles missing labels.

Demonstrates robustness across various data scales.

Abstract

Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance. We propose a novel deep neural networks (DNN) based model, Canonical Correlated AutoEncoder (C2AE), for solving this task. Aiming at better relating feature and label domain data for improved classification, we uniquely perform joint feature and label embedding by deriving a deep latent space, followed by the introduction of label-correlation sensitive loss function for recovering the predicted label outputs. Our C2AE is achieved by integrating the DNN architectures of canonical correlation analysis and autoencoder, which allows end-to-end learning and prediction with the ability to exploit label dependency. Moreover, our C2AE can be easily extended to address the learning problem with missing labels. Our experiments on multiple datasets with different scales confirm the effectiveness and robustness of our proposed method, which is shown to perform favorably against state-of-the-art methods for multi-label classification.