Deep Learning for Multi-label Classification

Abstract

In multi-label classification, the main focus has been to develop ways of learning the underlying dependencies between labels, and to take advantage of this at classification time. Developing better feature-space representations has been predominantly employed to reduce complexity, e.g., by eliminating non-helpful feature attributes from the input space prior to (or during) training. This is an important task, since many multi-label methods typically create many different copies or views of the same input data as they transform it, and considerable memory can be saved by taking advantage of redundancy. In this paper, we show that a proper development of the feature space can make labels less interdependent and easier to model and predict at inference time. For this task we use a deep learning approach with restricted Boltzmann machines. We present a deep network that, in an empirical evaluation, outperforms a number of competitive methods from the literature

Cited by in corpus (6)

• Tips, guidelines and tools for managing multi-label datasets: the mldr.datasets R package and the Cometa data repository
• Joint Binary Neural Network for Multi-label Learning with Applications to Emotion Classification
• Multi-label classification search space in the MEKA software
• CascadeML: An Automatic Neural Network Architecture Evolution and Training Algorithm for Multi-label Classification
• DeepHelp: Deep Learning for Shout Crisis Text Conversations
• Symbolic Music Loop Generation with VQ-VAE