Efficient Monte Carlo Methods for Multi-Dimensional Learning with Classifier Chains

Abstract

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance - at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest- performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

Submitted to Pattern Recognition

Cited by in corpus (10)

• Multi-Target Regression via Input Space Expansion: Treating Targets as Inputs
• Classifier Chains: A Review and Perspectives
• Scalable Multi-Output Label Prediction: From Classifier Chains to Classifier Trellises
• Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
• The Recycling Gibbs Sampler for Efficient Learning
• Multi-label Methods for Prediction with Sequential Data
• Deep Learning with a Rethinking Structure for Multi-label Classification
• Multilabel Classification with R Package mlr
• Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images
• Dynamic classifier chains for multi-label learning