Multi-Label Classification With Label-Specific Feature Generation: A Wrapped Approach

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 9; pp. 5199 - 5210
• Main Authors: Yu, Ze-Bang, Zhang, Min-Ling
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytical models; Classification; Comparative studies; Correlation; Decoupling; label correlation; label-specific features; Multi-label classification; Optimization; Predictive models; Regularization; Task analysis; Training; wrapped procedure; Wrapping
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2021.3070215

Label-specific features serve as an effective strategy to learn from multi-label data, where a set of features encoding specific characteristics of each label are generated to help induce multi-label classification model. Existing approaches work by taking the two-stage strategy, where the procedure of label-specific feature generation is independent of the follow-up procedure of classification model induction. Intuitively, the performance of resulting classification model may be suboptimal due to the decoupling nature of the two-stage strategy. In this paper, a wrapped learning approach is proposed which aims to jointly perform label-specific feature generation and classification model induction. Specifically, one (kernelized) linear model is learned for each label where label-specific features are simultaneously generated within an embedded feature space via empirical loss minimization and pairwise label correlation regularization. Comparative studies over a total of sixteen benchmark data sets clearly validate the effectiveness of the wrapped strategy in exploiting label-specific features for multi-label classification.