Multilabel Classification through Random Graph Ensembles

TL;DR

This paper introduces a novel ensemble learning approach for multilabel classification using random output graphs and kernel-based structured output learners, demonstrating competitive performance on benchmark datasets.

Contribution

The paper proposes a new random graph ensemble method for multilabel classification, enhancing diversity and performance over existing approaches.

Findings

Random graph ensembles outperform traditional methods on several benchmarks.

Ensemble diversity from output graph differences improves classification accuracy.

The approach is robust across heterogeneous multilabel datasets.

Abstract

We present new methods for multilabel classification, relying on ensemble learning on a collection of random output graphs imposed on the multilabel and a kernel-based structured output learner as the base classifier. For ensemble learning, differences among the output graphs provide the required base classifier diversity and lead to improved performance in the increasing size of the ensemble. We study different methods of forming the ensemble prediction, including majority voting and two methods that perform inferences over the graph structures before or after combining the base models into the ensemble. We compare the methods against the state-of-the-art machine learning approaches on a set of heterogeneous multilabel benchmark problems, including multilabel AdaBoost, convex multitask feature learning, as well as single target learning approaches represented by Bagging and SVM. In our experiments, the random graph ensembles are very competitive and robust, ranking first or second on most of the datasets. Overall, our results show that random graph ensembles are viable alternatives to flat multilabel and multitask learners.