Label distribution feature selection based on hierarchical structure and neighborhood granularity

• Published in: Information fusion 2024-12, Vol.112, p.102588, Article 102588
• Main Authors: Lu, Xiwen, Qian, Wenbin, Dai, Shiming, Huang, Jintao
• Format: Article
• Language: English
• Subjects: Feature selection; Granular computing; Hierarchical structure; Label distribution learning; Rough sets
• ISSN: 1566-2535; 1872-6305
• DOI: 10.1016/j.inffus.2024.102588

Label Distribution Learning (LDL) addresses label ambiguity in datasets but struggles with high-dimensional data due to irrelevant features. Label Distribution Feature Selection (LDFS) methods can effectively unravel the issues, but they often overlook the advantages of utilizing hierarchical relationships among data, which can improve feature discriminability. Furthermore, these methods inadequately consider the granulation process, directly affecting the important features’ identification. To overcome these challenges, this study proposes a novel LDFS approach incorporating hierarchical structures and neighborhood granularity. Our algorithm proceeds in three stages: initially, it forms a multi-granular representation of data to reveal hierarchical relationships; subsequently, in the granulation process, it employs a variable precision rough set model, leveraging neighborhood granularity for a nuanced feature relevance assessment; and finally, it synthesizes these findings via a fusion strategy, culminating in a hierarchical feature ranking. Extensive experiments are conducted on thirteen benchmark datasets against five different algorithms in terms of six evaluation metrics. The results show that our method outperforms competitors in about 80% of the cases, demonstrating its effectiveness and generalization. •A multi-granularity representation is presented to clarify the hierarchical structure of samples.•A variable precision-based neighborhood granularity is used to evaluate the feature relevance.•A novel fusion strategy-based feature selection is proposed for label distribution learning.•Extensive experiments demonstrate that the proposed algorithm is effective and feasible.