Feature Selection for Label Distribution Learning Based on Fuzzy Neighborhood Rough Set and Feature Interaction
DENG Dayong1,2, XU Jie2, DENG Zhixuan2, ZHENG Zhonglong2, LI Tianrui3
1. Xingzhi College, Zhejiang Normal University, Lanxi 321100; 2. School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004; 3. School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756
Abstract：Label distribution learning(LDL) is widely applied to handle label ambiguity. However,most algorithms are difficult to extract sufficient information from feature interactions. To address this issue, a method of feature selection for label distribution learning based on fuzzy neighborhood rough set and feature interaction(FNRI) is proposed to extract more interaction information from feature interactions. Firstly, a fuzzy dependency relation is introduced to measure the correlation between features and labels. The correlation among features is redefined, and a fuzzy neighborhood entropy is defined to quantify the interaction information between features. Secondly, a feature interaction evaluation index(FIE) based on feature interaction information is constructed. FIE is combined with a dynamic weighting function to calculate the importance of features. Experiments on 14 real-world datasets of LDL demonstrate the superior performance of FNRI.
邓大勇, 许捷, 邓志轩, 郑忠龙, 李天瑞. 基于模糊邻域粗糙集和特征交互的标记分布特征选择[J]. 模式识别与人工智能, 2026, 39(3): 250-260.
DENG Dayong, XU Jie, DENG Zhixuan, ZHENG Zhonglong, LI Tianrui. Feature Selection for Label Distribution Learning Based on Fuzzy Neighborhood Rough Set and Feature Interaction. Pattern Recognition and Artificial Intelligence, 2026, 39(3): 250-260.
[1] ZHAO X Y, AN Y X, XU N, et al. Variational Continuous Label Distribution Learning for Multi-label Text Classification. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(6): 2716-2729. [2] GENG X. Label Distribution Learning. IEEE Transactions on Know-ledge and Data Engineering, 2016, 28(7): 1734-1748. [3] SUN Y P, QI L Z, XU G. Classification of Extra-High Voltage Project Documents Based on Improved Multi-label Neural Network // Proc of the 5th International Conference on Applied Machine Lear-ning. Washington, USA: IEEE, 2023: 202-208. [4] CAO Q, LIU Y, WANG G X, et al. Building a Deep Learning Model for Multi-label Classification of Natural Disasters // Proc of the IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence. Washington, USA: IEEE, 2023: 505-509. [5] LI J, TANG H J, TANG D, et al. Multi-label Zero-Shot Learning for Industrial Fault Diagnosis // Proc of the 6th International Confe-rence on Information Communication and Signal Processing. Wa-shington, USA: IEEE, 2023: 1235-1240. [6] LE HOAI D, LIM E, CHOI E, et al. An Attention-Based Method for Multi-label Facial Action Unit Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2022: 2453-2458. [7] GENG X, LUO L R. Multilabel Ranking with Inconsistent Rankers // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 3742-3747. [8] HAN H S, SÖNMEZ E B. Facial Expression Recognition on Wild and Multi-label Faces with Deep Learning // Proc of the 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering. Washington, USA: IEEE, 2023. DOI: 10.1109/ICECCME57830.2023.10253453. [9] CHEN C, CHEN Z H, JIN X Y,et al. Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment. IEEE Journal of Biomedical and Health Informa-tics, 2022, 26(3): 1208-1218. [10] XUE D, HONG Z, GUO S Z, et al. Personality Recognition on Social Media with Label Distribution Learning. IEEE Access, 2017, 5: 13478-13488. [11] LING M G, GENG X. Indoor Crowd Counting by Mixture of Gau-ssians Label Distribution Learning. IEEE Transactions on Image Processing, 2019, 28(11): 5691-5701. [12] SCHÖLKOPF B, PLATT J C, SHAWE-TAYLOR J, et al. Estimating the Support of a High-Dimensional Distribution. Neural Computation, 2001, 13(7): 1443-1471. [13] ZHOU P, ZHANG Y Y, LING Z L, et al. Online Heterogeneous Streaming Feature Selection without Feature Type Information. IEEE Transactions on Big Data, 2024, 10(4): 470-485. [14] LIU J H, WEI W, LIN Y J, et al. Learning Implicit Labeling-Importance and Label Correlation for Multi-label Feature Selection with Streaming Labels. Pattern Recognition, 2024, 147. DOI: 10.1016/j.patcog.2023.110081. [15] ZHANG P, LIU G X, GAO W F, et al. Multi-label Feature Selec-tion Considering Label Supplementation. Pattern Recognition, 2021, 120. DOI: 10.1016/j.patcog.2021.108137. [16] QIAN W B, LONG X D, WANG Y L, et al. Multi-label Feature Selection Based on Label Distribution and Feature Complementarity. Applied Soft Computing, 2020, 90. DOI: 10.1016/j.asoc.2020.106167. [17] DENG Z X, LI T R, DENG D Y, et al. Feature Selection for Label Distribution Learning Using Dual-Similarity Based Neighborhood Fuzzy Entropy. Information Sciences, 2022, 615: 385-404. [18] ASH R B. Information Theory. New York, USA: Dover Publications, 1965. [19] PAWLAK Z, SKOWRON A. Rudiments of Rough Sets. Information Sciences, 2007, 177(1): 3-27. [20] WANG Z H, CHEN H M, YUAN Z, et al. Exploiting Fuzzy Rough Mutual Information for Feature Selection. Applied Soft Computing, 2022, 131. DOI: 10.1016/j.asoc.2022.109769. [21] QIAN W B, XU F K, HUANG J T, et al. A Novel Granular Ball Computing-Based Fuzzy Rough Set for Feature Selection in Label Distribution Learning. Knowledge-Based Systems, 2023, 278. DOI: 10.1016/j.knosys.2023.110898. [22] SHI E H, SUN L, XU J C, et al. Multilabel Feature Selection Using Mutual Information and ML-ReliefF for Multilabel Classification. IEEE Access, 2020, 8: 145381-145400. [23] XU F F, MIAO D Q, WEI L. Fuzzy-Rough Attribute Reduction via Mutual Information with an Application to Cancer Classifica-tion. Computers and Mathematics with Applications, 2009, 57(6): 1010-1017. [24] ZHANG X Y, ZHAO W C. Uncertainty Measures and Feature Selection Based on Composite Entropy for Generalized Multigranulation Fuzzy Neighborhood Rough Set. Fuzzy Sets and Systems, 2024, 486. DOI: 10.1016/j.fss.2024.108971. [25] DENG D Y, XU J, DENG Z X, et al. Feature Selection Based on Fuzzy Joint Entropy and Feature Interaction for Label Distribution Learning. Information Processing and Management, 2025, 62(6). DOI: 10.1016/j.ipm.2025.104234. [26] LEE J, KIM D W. SCLS: Multi-label Feature Selection Based on Scalable Criterion for Large Label Set. Pattern Recognition, 2017, 66: 342-352. [27] ZHANG J, LUO Z M, LI C D, et al. Manifold Regularized Discriminative Feature Selection for Multi-label Learning. Pattern Recognition, 2019, 95: 136-150. [28] ZHANG J, LIN Y D, JIANG M, et al. Fast Multilabel Feature Selection via Global Relevance and Redundancy Optimization. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(4): 5721-5734. [29] DENG D Y, CHEN T, DENG Z X, et al. Dynamic Feature Selection Based on F-Fuzzy Rough Set for Label Distribution Learning. International Journal of Fuzzy Systems, 2024, 26(8): 2688-2706.
2026, Vol. 39 
