|Table of Contents|

Multi-Label Feature Selection Based on Neighborhood Approximation Error Rate(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2023年01期
Page:
66-74
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
Multi-Label Feature Selection Based on Neighborhood Approximation Error Rate
Author(s):
Pan Siyuan1; 2; Liu Yuankui1; 2; Mao Yu1; 2; Lin Yaojin1; 2
(1.School of Computer Science,Minnan Normal University,Zhangzhou 363000,China) (2.Fujian Key Laboratory of Granular Computing and Application,School of Computer Science,Minnan Normal University,Zhangzhou 363000,China)
Keywords:
multi-label learning; feature selection; neighborhood approximation error rate
PACS:
O643/X703
DOI:
10.3969/j.issn.1672-1292.2023.01.009
Abstract:
Multi-label learning can process data associated with a set of labels simultaneously, and the study of multi-label learning is very important for learning modeling of polysemous objects. As with traditional single-label learning, the high dimensionality of data is an obstacle to multi-label learning, so data dimensionality reduction is a very important task, and feature selection is an effective data dimensionality reduction technique. A multi-label feature selection algorithm is proposed on the basis of the neighborhood approximation error rate. Firstly, based on the neighborhood rough set theory, the boundaries of instances are introduced to granularize all instances. Secondly, a neighborhood approximation error rate strategy is proposed to evaluate features based on the neighborhood decision error rate. Finally, extensive experiments are conducted on publicly available datasets.The results show the effectiveness of the proposed algorithm.

References:

[1]FAKHARI A,MOGHADAM A. Combination of classification and regression in decision tree for multi-labeling image annotation and retrieval[J]. Applied Soft Computing,2013,13(2):1292-1302.
[2]GAO W,ZHOU Z H. On the consistency of multi-label learning[C]//Proceedings of the 24th Annual Conference on Learning Theory. PMLR 19:341-358,2011.
[3]GU Q,LI Z,HAN J. Correlated multi-label feature selection[C]//Proceedings of the 20th ACM International Conference on Information and Knowledge Management. Glasgow,Scotland:Association for Computing Machinery,2011.
[4]DAI J H,XU Q. Attribute selection based on information gain ratio in fuzzy rough set theory with application to tumor classification[J]. Applied Soft Computing,2013,13(1):211-221.
[5]LIN Y J,HU Q H,LIU J H,et al. Multi-label feature selection based on neighborhood mutual information[J]. Applied Soft Computing,2016,38:244-256.
[6]SECHIDIS K,NIKOLAOU N,BROWN G. Information theoretic feature selection in multi-label data through composite likelihood[C]//Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition(SPR)and Structural and Syntactic Pattern Recognition(SSPR). Joensuu,Finland,2014.
[7]SPOLAOR N,CHERMAN E A,MONARD M C,et al. A comparison of multi-label feature selection methods using the problem transformation approach[J]. Electronic Notes in Theoretical Computer Science,2013,292:135-151.
[8]SPOLAOR N,MONARD M C,TSOUMAKAS G,et al. Label construction for multi-label feature selection[C]//2014 Brazilian Conference on Intelligent Systems. San Carlos,Venezuela,2014.
[9]SLAVKOV I,KARCHESKA J,KOCEV D,et al. ReliefF for hierarchical multi-label classification[J]. International Workshop on New Frontiers in Mining Complex Patterns. Springer,Cham,2013:148-161.
[10]GHARROUDI,ELGHAZEL,AUSSEM. A comparison of multi-label feature selection methods using the random forest paradigm[C]//Canadian Conference on Artificial Intelligence. Montreal,QC,Canada,2014.
[11]段洁,胡清华,张灵均,等. 基于邻域粗糙集的多标记分类特征选择算法[J]. 计算机研究与发展,2015,52(1):56-65.
[12]HU Q H,PEDRYCZ W,YU D R,et al. Selecting discrete and continuous features based on neighborhood error minimization[J]. IEEE Transactions on Systems,Man and Cybernetics,Part B,2009,40(1):137-150.
[13]GAO T L,JIA X H,JIANG R,et al. SaaS service combinatorial trustworthiness measurement method based on Markov Theory and cosine similarity[J]. Security and Communication Networks,2022:7080367.
[14]陈超逸,林耀进,唐莉,等. 基于邻域交互增益信息的多标记流特征选择算法[J]. 南京大学学报(自然科学),2020,56(1):30-40.
[15]ZHANG M L,PENA J M,ROBLES V. Feature selection for multi-label naive bayes classification[J]. Information Sciences,2009,179(19):3218-3229.
[16]ZHANG Y,ZHOU Z H. Multi-label dimensionality reduction via dependence maximization[J]. ACM Transactions on Knowledge Discovery from Data,2010,4(3):1-21.
[17]LEE J,KIM D W. Feature selection for multi-label classification using multivariate mutual information[J]. Pattern Recognition Letters,2013,34(3):349-357.
[18]卢舜,林耀进,吴镒潾,等. 基于多粒度一致性邻域的多标记特征选择[J]. 南京大学学报(自然科学),2022,58(1):60-70.
[19]FRIEDMAN M. A comparison of alternative tests of significance for the problem of m rankings[J]. The Annals of Mathematical Statistics,1940,11(1):86-92.
[20]NEMENYI P B. Distribution-free multiple comparisons[M]. Princeton,State of New Jersey:Princeton University,1963.

Memo

Memo:
-
Last Update: 2023-03-15