多标记数据驱动的可变换算子值核

汪振鑫; 陈德刚; 车晓雅

doi:10.11992/tis.202503021

Chinese

您当前的位置：

首页 >

文章列表页 >

多标记数据驱动的可变换算子值核

学术论文—机器学习 | 更新时间：2026-05-01

- 多标记数据驱动的可变换算子值核
- Transformable operator-valued kernels driven by multi-label datasets
- 智能系统学报 2026年21卷第2期页码：365-374
- 作者机构：
  
  1. 华北电力大学控制与计算机工程学院,北京,102200
  2. 华北电力大学数理学院,北京,102200
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目（12571496,12201213）.
- DOI：10.11992/tis.202503021
  中图分类号： TP181
- 网络首发：2026-03-05，
  
  纸质出版：2026
- 稿件说明：
移动端阅览
[1]汪振鑫,陈德刚,车晓雅.多标记数据驱动的可变换算子值核[J].智能系统学报,2026,21(2):365-374.

[doi:10.11992/tis.202503021]
[1]汪振鑫,陈德刚,车晓雅.多标记数据驱动的可变换算子值核[J].智能系统学报,2026,21(2):365-374. DOI： 10.11992/tis.202503021.

[doi:10.11992/tis.202503021] DOI：

摘要

算子值核是取值为希尔伯特空间上算子的二元函数，在机器学习领域中旨在更好地描述多任务学习中不同任务之间的关联性。多标记学习是一种特殊的多任务学习，本文基于核对齐方法从多标记数据集中学习算子值核并构建多标记学习的预测模型。1)利用核对齐方法学习样例级特征重要度分布；2)基于样例级特征重要度分布构造算子值核，证明其不仅是偏迹核而且是可变换算子值核，且其对应核矩阵中的每个分块刻画了样例间标记相关性的交互信息；3)设计基于可变换算子值核的多标记学习算法，在9个多标记数据集上与4种高性能算法进行对比实验，结果验证了所提算法的有效性。

Abstract

An operator-valued kernel is a binary function that takes the value of an operator on Hilbert space

which in the field of machine learning aims to better describe the correlation between different tasks in multi-task learning. Multi-label learning is a special kind of multi-task learning

in this paper

we learn operator-valued kernels from multi-label datasets based on the kernel alignment method and construct a prediction model for multi-label learning. Firstly

we use kernel alignment method to learn the instance-level feature importance distribution; secondly

we construct operator-valued kernel based on the instance-level feature importance distribution

and prove that it is not only partial trace kernel but also transformable operator-valued kernel

and that each block of its corresponding kernel matrix depicts the interaction information of label correlation among the samples; lastly

we design the multi-label learning algorithms based on transformable operator-valued kernel

and conduct comparative experiments with four high-performance algorithms on nine multi-label datasets

the results verify effectiveness of our proposed algorithm.

关键词

Keywords

references

BROUARD C, SHEN Huibin, D?HRKOP K, et al. Fast metabolite identification with input output kernel regression[J]. Bioinformatics, 2016, 32(12): i28-i36.

KADRI H, RAKOTOMAMONJY A, PREUX P, et al. Multiple operator-valued kernel learning[J]. Advances in neural information processing systems, 2012, 25(3): 2429-2437.

KADRI H, DUFLOS E, PREUX P, et al. Operator-valued kernels for learning from functional response data[J]. Journal of machine learning research, 2016, 17(20): 1-54.

HUUSARI R, KADRI H. Entangled kernels-beyond separability[J]. Journal of machine learning research, 2021, 22(24): 1-40.

DINUZZO F, FUKUMIZU K, HSU C, et al. Low-rank output kernels[J]. Journal of machine learning research, 2011, 20: 181-196.

DINUZZO F, ONG C S, PILLONETTO G, et al. Learning output kernels with block coordinate descent[C]//Proceedings of the 28th International Conference on Machine Learning. Bellevue: PMLR, 2011: 49-56.

?LVAREZ M A, ROSASCO L, LAWRENCE N D. Kernels for vector-valued functions: a review[J]. Foundations and trends? in machine learning, 2012, 4(3): 195-266.

LIM N, D’ALCH?-BUC F, AULIAC C, et al. Operator-valued kernel-based vector autoregressive models for network inference[J]. Machine learning, 2015, 99(3): 489-513.

GREGOROV? M, KALOUSIS A, MARCHAND-MAILLET S. Forecasting and granger modelling with non-linear dynamical dependencies[C]//Machine Learning and Knowledge Discovery in Databases. Cham: Springer International Publishing, 2017: 544-558.

MINH H Q, BAZZANI L, MURINO V. A unifying framework in vector-valued reproducing kernel Hilbert spaces for manifold regularization and co-regularized multi-view learning[J]. Journal of machine learning research, 2016, 17(25): 1-72.

HUUSARI R, KADRI H, CAPPONI C. Multi-view metric learning in vector-valued kernel spaces[C]//International Conference on Artificial Intelligence and Statistics. Playa Blanca: PMLR, 2018: 415-424.

ZHANG Minling, ZHOU Zhihua. ML-KNN: a lazy learning approach to multi-label learning[J]. Pattern recognition, 2007, 40(7): 2038-2048.

ZHANG Yin, ZHOU Zhihua. Multilabel dimensionality reduction via dependence maximization[J]. ACM transactions on knowledge discovery from data, 2010, 4(3): 1-21.

LI Yuwen, LIN Yaojin, LIU Jinghua, et al. Feature selection for multi-label learning based on kernelized fuzzy rough sets[J]. Neurocomputing, 2018, 318: 271-286.

HASHEMI A, BAGHER DOWLATSHAHI M, NEZAMABADI-POUR H. An efficient Pareto-based feature selection algorithm for multi-label classification[J]. Information sciences, 2021, 581: 428-447.

HASHEMI A, DOWLATSHAHI M B. MLCR: a fast multi-label feature selection method based on K-means and L2-norm[C]//2020 25th International Computer Conference, Computer Society of Iran. Tehran: IEEE, 2020: 1-7.

LIN Yaojin, HE Zhuoxin, GUO Lei, et al. Multi-label feature selection via positive or negative correlation[J]. IEEE transactions on emerging topics in computational intelligence, 2024, 8(1): 401-415.

AFDHAL D, ANANTA K W, HARTONO W S. Adverse drug reactions prediction using multi-label linear discriminant analysis and multi-label learning[C]//2020 International Conference on Advanced Computer Science and Information Systems. Depok: IEEE, 2020: 69-76.

MULIMANI M, MESAROS A. Class-incremental learning for multi-label audio classification[C]//2024 IEEE International Conference on Acoustics, Speech and Signal Processing. Seoul: IEEE, 2024: 916-920.

CHEN Jiayao, LI Shaoyuan. Class-aware learning for imbalanced multi-label classification[C]//2023 IEEE 5th International Conference on Civil Aviation Safety and Information Technology. Dali: IEEE, 2023: 903-907.

GE Yuhang, HU Xuegang, LI Peipei, et al. Multi-label learning with data self-augmentation[C]//Neural Information Processing. Singapore: Springer Nature Singapore, 2023: 336-347.

CHE Xiaoya, CHEN Degang, MI Jusheng. Learning instance-level label correlation distribution for multilabel classification with fuzzy rough sets[J]. IEEE transactions on fuzzy systems, 2023, 31(8): 2871-2884.

CRISTIANINI N, SHAWE-TAYLOR J, ELISSEEFF A, et al. On kernel-target alignment[J]. Advances in neural information processing systems, 2002: 367-374.

DOMINGOS P. A few useful things to know about machine learning[J]. Communications of the ACM, 2012, 55(10): 78-87.

ZHANG Junping, WANG Feiyue, WANG Kunfeng, et al. Data-driven intelligent transportation systems: a survey[J]. IEEE transactions on intelligent transportation systems, 2011, 12(4): 1624-1639.

AMRI M M, ABED S A. The data-driven future of healthcare: a review[J]. Mesopotamian journal of big data, 2023, 2023: 68-74.

SCHAPIRE R E, SINGER Y. BoosTexter: a boosting-based system for text categorization[J]. Machine learning, 2000, 39(2): 135-168.

WU Xizhu, ZHOU Zhihua. A unified view of multi-label performance measures[C]//International Conference on Machine Learning. Sydney: PMLR, 2017: 3780-3788.

SALEM N, HUSSEIN S. Data dimensional reduction and principal components analysis[J]. Procedia computer science, 2019, 163: 292-299.

CHEN Linlin, CHEN Degang, WANG Hui. Alignment based kernel selection for multi-label learning[J]. Neural processing letters, 2019, 49(3): 1157-1177.

CARMELI C, DE VITO E, TOIGO A. Vector valued reproducing kernel Hilbert spaces of integrable functions and mercer theorem[J]. Analysis and applications, 2006, 4(4): 377-408.

SZAB? Z, SRIPERUMBUDUR B K, P?CZOS B, et al. Learning theory for distribution regression[J]. Journal of machine learning research, 2016, 17(152): 1-40.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

结合局部标记序关系的弱监督标记分布学习

基于加权信息粒化的多标记数据特征选择算法

自适应标记关联与实例关联诱导的缺失多视图弱标记学习

代价敏感数据的多标记特征选择算法

弹性网络核极限学习机的多标记学习算法