UNIT: A unified metric learning framework based on maximum entropy regularization | |
Deng, Huiyuan2; Meng, Xiangzhu3; Deng, Fengxia1; Feng, Lin2 | |
刊名 | APPLIED INTELLIGENCE |
2023-07-26 | |
页码 | 21 |
关键词 | Metric learning Kernel learning Nearest-neighbors classification Semi-supervised learning Maximum entropy principle |
ISSN号 | 0924-669X |
DOI | 10.1007/s10489-023-04831-x |
通讯作者 | Feng, Lin(fenglin@dlut.edu.cn) |
英文摘要 | Metric learning has emerged as a critical tool for analyzing the semantic similarities between objects. However, numerous existing methods are incapable of simultaneously maximizing the proximity of similar pairs and the separability between dissimilar ones to achieve the largest margin principle. Additionally, most graph Laplacian-based semi-supervised approaches fail to consider the valuable dissimilar information of unlabeled data, and they treat neighborhood graph construction and metric learning as separate procedures, thereby breaking the unified relationship between these two components. To overcome these challenges, this paper proposes a scalable and efficient metric learning framework called Unified metric learNing based on maxIum enTropy (UNIT). UNIT attempts to unify supervised and semi-supervised metric learning into a framework by introducing the maximum entropy regularizer of the eigenvalues of the learned matrix. With the novel regularizer, UNIT can maximize the closeness of similar instances and the separability of dissimilar ones without encountering the trivial solution problem. Furthermore, the adaptive graph Laplacian, formulated by a similar graph as well as a dissimilar graph, is constructed to mine the rich discriminant information of the unlabeled data. We demonstrate that UNIT can be solved efficiently with the alternating direction method, with each sub-problem being solvable using a closed-form solution. To account for nonlinear data distribution, a kernelized version of UNIT is also provided. The effectiveness of the proposed methods is validated through extensive supervised and semi-supervised experiments on various datasets. |
WOS关键词 | EIGENVALUE |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | SPRINGER |
WOS记录号 | WOS:001037138200002 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/53819] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Feng, Lin |
作者单位 | 1.Harbin Inst Technol, State Key Lab Urban Water Resources & Environm, Harbin 150090, Peoples R China 2.Dalian Univ Technol, Sch Comp Sci & Technol, Dalian 116024, Peoples R China 3.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Deng, Huiyuan,Meng, Xiangzhu,Deng, Fengxia,et al. UNIT: A unified metric learning framework based on maximum entropy regularization[J]. APPLIED INTELLIGENCE,2023:21. |
APA | Deng, Huiyuan,Meng, Xiangzhu,Deng, Fengxia,&Feng, Lin.(2023).UNIT: A unified metric learning framework based on maximum entropy regularization.APPLIED INTELLIGENCE,21. |
MLA | Deng, Huiyuan,et al."UNIT: A unified metric learning framework based on maximum entropy regularization".APPLIED INTELLIGENCE (2023):21. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论