Learning With Multiclass AUC: Theory and Algorithms

doi:10.1109/TPAMI.2021.3101125

	Learning With Multiclass AUC: Theory and Algorithms
	Yang, Zhiyong 1; Xu, Qianqian 2; Bao, Shilong 3,4; Cao, Xiaochun 3,5; Huang, Qingming 2,6,7
	2022-11-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	44 期号:11 页码:7747-7763
摘要	The Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. The vast majority of existing AUC-optimization-based machine learning methods only focus on binary-class cases, while leaving the multiclass cases unconsidered. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics. Our foundation is based on the M metric, which is a well-known multiclass extension of AUC. We first pay a revisit to this metric, showing that it could eliminate the imbalance issue from the minority class pairs. Motivated by this, we propose an empirical surrogate risk minimization framework to approximately optimize the M metric. Theoretically, we show that: (i) optimizing most of the popular differentiable surrogate losses suffices to reach the Bayes optimal scoring function asymptotically; (ii) the training framework enjoys an imbalance-aware generalization error bound, which pays more attention to the bottleneck samples of minority classes compared with the traditional O(root 1/N) THORN result. Practically, to deal with the low scalability of the computational operations, we propose acceleration methods for three popular surrogate loss functions, including the exponential loss, squared loss, and hinge loss, to speed up loss and gradient evaluations. Finally, experimental results on 11 real-world datasets demonstrate the effectiveness of our proposed framework. The code is now available at https://github.com/joshuaas/ Learning-with-Multiclass-AUC-Theory-and-Algorithms.
关键词	AUC optimization machine learning
DOI	10.1109/TPAMI.2021.3101125
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102003] ; National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[62025604] ; National Natural Science Foundation of China[61861166002] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[61836002] ; National Natural Science Foundation of China[61976202] ; Fundamental Research Funds for the Central Universities ; National Postdoctoral Program for Innovative Talents[BX2021298] ; Youth Innovation Promotion Association CAS ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB28000000]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000864325900036
出版者	IEEE COMPUTER SOC
引用统计	被引频次：26[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19765
专题	中国科学院计算技术研究所期刊论文
通讯作者	Xu, Qianqian; Huang, Qingming
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing 100093, Peoples R China 4.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 100049, Peoples R China 5.Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen 518100, Peoples R China 6.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Key Lab Big Data Min & Knowledge Management BDKM, Beijing 101408, Peoples R China 7.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Yang, Zhiyong,Xu, Qianqian,Bao, Shilong,et al. Learning With Multiclass AUC: Theory and Algorithms[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2022,44(11):7747-7763.
APA	Yang, Zhiyong,Xu, Qianqian,Bao, Shilong,Cao, Xiaochun,&Huang, Qingming.(2022).Learning With Multiclass AUC: Theory and Algorithms.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,44(11),7747-7763.
MLA	Yang, Zhiyong,et al."Learning With Multiclass AUC: Theory and Algorithms".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44.11(2022):7747-7763.