Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization

In multilabel learning, each instance in the training set is associated with a set of labels and the task is to output a label set whose size is unknown a priori for each unseen instance. In this paper, this problem is addressed in the way that a neural network algorithm named BP-MLL, i.e., Backpropagation for Multilabel Learning, is proposed. It is derived from the popular Backpropogation algorithm through employing a novel error function capturing the characteristics of multilabel learning, i.e., the labels belonging to an instance should be ranked higher than those not belonging to that instance. Applications to two real-world multilabel learning problems, i.e., functional genomics and text categorization, show that the performance of BP-MLL is superior to that of some well-established multilabel learning algorithms.

1 Introduction

Multilabel learning tasks are ubiquitous in real-world problems. For instance, in text categorization, each document may belong to several predefined topics, such as government and health [18], [28]; in bioinformatics, each gene may be associated with a set of functional classes, such as metabolism, transcription and protein synthesis [8]; in scene classification, each scene image may belong to several semantic classes, such as beach and urban [2]. In all these cases, instances in the training set are each associated with a set of labels and the task is to output the label set whose size is not known a priori for the unseen instance.