Collaborative Learning of Label Semantics and Deep Label-Specific Features for Multi-Label Classification

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 12; pp. 9860 - 9871
• Main Authors: Hang, Jun-Yi, Zhang, Min-Ling
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Classification; Collaboration; collaborative learning; Correlation; Deep learning; Encoding; Feature extraction; label semantics; label-specific features; Learning; Machine learning; multi-label classification; Representation learning; Semantic relations; Semantics
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2021.3136592

In multi-label classification, the strategy of label-specific features has been shown to be effective to learn from multi-label examples by accounting for the distinct discriminative properties of each class label. However, most existing approaches exploit the semantic relations among labels as immutable prior knowledge, which may not be appropriate to constrain the learning process of label-specific features. In this paper, we propose to learn label semantics and label-specific features in a collaborative way. Accordingly, a deep neural network (DNN) based approach named Clif , i.e., C ollaborative L earning of label semant I cs and deep label-specific F eatures for multi-label classification , is proposed. By integrating a graph autoencoder for encoding semantic relations in the label space and a tailored feature-disentangling module for extracting label-specific features, Clif is able to employ the learned label semantics to guide mining label-specific features and propagate label-specific discriminative properties to the learning process of the label semantics. In such a way, the learning of label semantics and label-specific features interact and facilitate with each other so that label semantics can provide more accurate guidance to label-specific feature learning. Comprehensive experiments on 14 benchmark data sets show that our approach outperforms other well-established multi-label classification algorithms.