ML-kNN: A lazy learning approach to multi-label learning

Abstract: Multi-label learning originated from the investigation of text cat-egorization problem, where each document may belong to several predefined topics simultaneously. In multi-label learning, the training set is composed of instances each associated with a set of labels, and the task is to predict the la-bel sets of unseen instances through analyzing training instances with known label sets. In this paper, a multi-label lazy learning approach named Ml-knn is presented, which is derived from the traditional k-Nearest Neighbor (kNN) algorithm. In detail, for each unseen instance, its k nearest neighbors in the training set are firstly identified. After that, based on statistical in-formation gained from the label sets of these neighboring instances, i.e. the number of neighboring instances belonging to each possible class, maximum a posteriori (MAP) principle is utilized to determine the label set for the unseen instance. Experiments on three different real-world multi-label learn-ing problems, i.e. Yeast gene functional analysis, natural scene classification and automatic web page categorization, show thatMl-knn achieves superior performance to some well-established multi-label learning algorithms. Summary: In this paper, a lazy learning algorithm named Ml-knn, which is the multi-label version of kNN, is proposed. Based on statistical informa-tion derived from the label sets of an unseen instance’s neighboring instances, Ml-knn utilizes maximum a posteriori principle to determine the label set for the unseen instance. Experiments on three real-world multi-label learn-ing problems, i.e. Yeast gene functional analysis, natural scene classification and automatic web page categorization, show thatMl-knn outperforms some well-established multi-label learning algorithms