Convergence analysis for complementary-label learning with kernel ridge regression  

作　　者：NIE Wei-lin WANG Cheng XIE Zhong-hua 

机构地区：[1]School of Mathematics and Statistics,Huizhou University,Huizhou 516007,China [2]School of Computer Science and Engineering,Huizhou University,Huizhou 516007,China

出　　处：《Applied Mathematics(A Journal of Chinese Universities)》2024年第3期533-544,共12页高校应用数学学报（英文版）（B辑）

基　　金：Supported by the Indigenous Innovation’s Capability Development Program of Huizhou University(HZU202003,HZU202020);Natural Science Foundation of Guangdong Province(2022A1515011463);the Project of Educational Commission of Guangdong Province(2023ZDZX1025);National Natural Science Foundation of China(12271473);Guangdong Province’s 2023 Education Science Planning Project(Higher Education Special Project)(2023GXJK505)。

摘　　要：Complementary-label learning(CLL)aims at finding a classifier via samples with complementary labels.Such data is considered to contain less information than ordinary-label samples.The transition matrix between the true label and the complementary label,and some loss functions have been developed to handle this problem.In this paper,we show that CLL can be transformed into ordinary classification under some mild conditions,which indicates that the complementary labels can supply enough information in most cases.As an example,an extensive misclassification error analysis was performed for the Kernel Ridge Regression(KRR)method applied to multiple complementary-label learning(MCLL),which demonstrates its superior performance compared to existing approaches.

关 键 词：multiple complementary-label learning partial label learning error analysis reproducing kernel Hilbert spaces 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]