Three-way decision with co-training for partially labeled data

Abstract The theory of three-way decision plays an important role in decision making and knowledge reasoning. However, little attention has been paid to the problem of learning from partially labeled data with three-way decision. In this paper, we propose a three-way co-decision model for partially labeled data. More specifically, the problem of attribute reduction for partially labeled data is first investigated, and two semi-supervised attribute reduction algorithms based on novel confidence discernibility matrix are proposed. Then, a three-way co-decision model is introduced to classify unlabeled data into useful, useless, and uncertain data, and the model is iteratively retrained on the carefully selected useful data to improve its performance. Moreover, we theoretically analyze the effectiveness of the proposed model. The experimental results conducted on UCI data sets demonstrate that the proposed model is promising, and even compares favourably with the single supervised classifier trained on all training data with true labels.

[1]  Yiyu Yao,et al.  The superiority of three-way decisions in probabilistic rough set models , 2011, Inf. Sci..

[2]  Zdzis?aw Pawlak,et al.  Rough sets , 2005, International Journal of Computer & Information Sciences.

[3]  Yiyu Yao,et al.  A Decision Theoretic Framework for Approximating Concepts , 1992, Int. J. Man Mach. Stud..

[4]  Qinghua Hu,et al.  Attribute Selection for Partially Labeled Categorical Data By Rough Set Approach , 2017, IEEE Transactions on Cybernetics.

[5]  Hualong Yu,et al.  Rough set based semi-supervised feature selection via ensemble selector , 2019, Knowl. Based Syst..

[6]  Yiyu Yao,et al.  Three-way decision and granular computing , 2018, Int. J. Approx. Reason..

[7]  Yiyu Yao,et al.  Constructing shadowed sets and three-way approximations of fuzzy sets , 2017, Inf. Sci..

[8]  Zhi-Hua Zhou,et al.  Semi-supervised learning by disagreement , 2010, Knowledge and Information Systems.

[9]  Qinghua Hu,et al.  Neighborhood rough set based heterogeneous feature subset selection , 2008, Inf. Sci..

[10]  Yiyu Yao,et al.  Three-Way Decisions and Cognitive Computing , 2016, Cognitive Computation.

[11]  Caihui Liu,et al.  Novel matrix-based approaches to computing minimal and maximal descriptions in covering-based rough sets , 2020, Inf. Sci..

[12]  Xiuyi Jia,et al.  A co-training approach for sequential three-way decisions , 2020, Int. J. Mach. Learn. Cybern..

[13]  Sam Kwong,et al.  Fuzzy-Rough-Set-Based Active Learning , 2014, IEEE Transactions on Fuzzy Systems.

[14]  HerreraFrancisco,et al.  Self-labeled techniques for semi-supervised learning , 2015 .

[15]  Rayid Ghani,et al.  Analyzing the effectiveness and applicability of co-training , 2000, CIKM '00.

[16]  Witold Pedrycz,et al.  Principles for constructing three-way approximations of fuzzy sets: A comparative evaluation based on unsupervised learning , 2020, Fuzzy Sets Syst..

[17]  Eric C. C. Tsang,et al.  Neighborhood attribute reduction approach to partially labeled data , 2018, Granular Computing.

[18]  D. Angluin,et al.  Learning From Noisy Examples , 1988, Machine Learning.

[19]  Zhi-Hua Zhou,et al.  A brief introduction to weakly supervised learning , 2018 .

[20]  Yiyu Yao,et al.  Discernibility matrix simplification for constructing attribute reducts , 2009, Inf. Sci..

[21]  Yiyu Yao,et al.  Probabilistic rough set approximations , 2008, Int. J. Approx. Reason..

[22]  Andrzej Skowron,et al.  Local rough set: A solution to rough data analysis in big data , 2018, Int. J. Approx. Reason..

[23]  Jianhua Dai,et al.  Feature selection via normative fuzzy information weight with application into tumor classification , 2020, Appl. Soft Comput..

[24]  Yiyu Yao,et al.  Attribute reduction in decision-theoretic rough set models , 2008, Inf. Sci..

[25]  Cheng-Chien Kuo,et al.  A Semi-Supervised Learning Algorithm for Data Classification , 2015, Int. J. Pattern Recognit. Artif. Intell..

[26]  Wei-Zhi Wu,et al.  Maximal-Discernibility-Pair-Based Approach to Attribute Reduction in Fuzzy Rough Sets , 2018, IEEE Transactions on Fuzzy Systems.

[27]  Hamido Fujita,et al.  Fuzzy neighborhood covering for three-way classification , 2020, Inf. Sci..

[28]  Sheela Ramanna,et al.  Learning relational facts from the web: A tolerance rough set approach , 2015, Pattern Recognit. Lett..

[29]  Zhifei Zhang,et al.  International Journal of Approximate Reasoning Diverse Reduct Subspaces Based Co-training for Partially Labeled Data , 2022 .

[30]  Xiaojin Zhu,et al.  Introduction to Semi-Supervised Learning , 2009, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[31]  Janusz Zalewski,et al.  Rough sets: Theoretical aspects of reasoning about data , 1996 .

[32]  Richard Jensen,et al.  Fuzzy-rough set based semi-supervised learning , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[33]  Qinghua Hu,et al.  DualPOS: A Semi-supervised Attribute Selection Approach for Symbolic Data Based on Rough Set Theory , 2016, WAIM.

[34]  Yiyu Yao,et al.  Tri-level thinking: models of three-way decision , 2020, Int. J. Mach. Learn. Cybern..

[35]  Zhi-Hua Zhou,et al.  Semi-supervised learning by disagreement , 2010, Knowledge and Information Systems.

[36]  Andrzej Skowron,et al.  The Discernibility Matrices and Functions in Information Systems , 1992, Intelligent Decision Support.

[37]  Yiyu Yao,et al.  Three-way conflict analysis: Reformulations and extensions of the Pawlak model , 2019, Knowl. Based Syst..

[38]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[39]  Yiyu Yao,et al.  Three-way decisions with probabilistic rough sets , 2010, Inf. Sci..

[40]  Guoyin Wang,et al.  A survey on rough set theory and its applications , 2016, CAAI Trans. Intell. Technol..

[41]  Francisco Herrera,et al.  Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study , 2015, Knowledge and Information Systems.

[42]  Fan Min,et al.  Tri-partition cost-sensitive active learning through kNN , 2017, Soft Computing.

[43]  Xin Yang,et al.  A unified framework of dynamic three-way probabilistic rough sets , 2017, Inf. Sci..

[44]  Jiye Liang,et al.  Local multigranulation decision-theoretic rough sets , 2017, Int. J. Approx. Reason..

[45]  Bo Yang,et al.  Complex network analysis of three-way decision researches , 2020, International Journal of Machine Learning and Cybernetics.

[46]  Yiyu Yao,et al.  Three-way granular computing, rough sets, and formal concept analysis , 2020, Int. J. Approx. Reason..

[47]  Yiyu Yao,et al.  Covering based rough set approximations , 2012, Inf. Sci..

[48]  Min Chen,et al.  Semi-supervised Rough Cost/Benefit Decisions , 2009, Fundam. Informaticae.

[49]  Qinghua Hu,et al.  Neighbor Inconsistent Pair Selection for Attribute Reduction by Rough Set Approach , 2018, IEEE Transactions on Fuzzy Systems.

[50]  Bingyang Li,et al.  Feature Selection for Partially Labeled Data Based on Neighborhood Granulation Measures , 2019, IEEE Access.