CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
Unsupervised Ranking of Multi-Attribute Objects Based on Principal Curves
Li, Chun-Guo1,2; Mei, Xing1; Hu, Bao-Gang1
Source PublicationIEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
2015-12-01
Volume27Issue:12Pages:3404-3416
SubtypeArticle
AbstractUnsupervised ranking faces one critical challenge in evaluation applications, that is, no ground truth is available. When PageRank and its variants show a good solution in related objects, they are applicable only for ranking from link-structure data. In this work, we focus on unsupervised ranking from multi-attribute data which is also common in evaluation tasks. To overcome the challenge, we propose five essential meta-rules for the design and assessment of unsupervised ranking approaches: scale and translation invariance, strict monotonicity, compatibility of linearity and nonlinearity, smoothness, and explicitness of parameter size. These meta-rules are regarded as high level knowledge for unsupervised ranking tasks. Inspired by the works in [ 12] and [ 35], we propose a ranking principal curve (RPC) model, which learns a one-dimensional manifold function to perform unsupervised ranking tasks on multi-attribute observations. Furthermore, the RPC is modeled to be a cubic Bezier curve with control points restricted in the interior of a hypercube, complying with all the five meta-rules to infer a reasonable ranking list. With control points as model parameters, one is able to understand the learned manifold and to interpret and visualize the ranking results. Numerical experiments of the presented RPC model are conducted on two open datasets of different ranking applications. In comparison with the state-of-the-art approaches, the new model is able to show more reasonable ranking lists.
KeywordUnsupervised Ranking Multi-attribute Meta-rules Data Skeleton Principal Curves Bezier Curves
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TKDE.2015.2441692
WOS KeywordDESIGN
Indexed BySCI
Language英语
Funding OrganizationNSFC(61273196 ; 61271430 ; 61332017)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS IDWOS:000364853800019
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10510
Collection模式识别国家重点实验室_多媒体计算与图形学
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Hebei Univ, Coll Math & Informat Sci, Baoding 071002, Hebei, Peoples R China
Recommended Citation
GB/T 7714
Li, Chun-Guo,Mei, Xing,Hu, Bao-Gang. Unsupervised Ranking of Multi-Attribute Objects Based on Principal Curves[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2015,27(12):3404-3416.
APA Li, Chun-Guo,Mei, Xing,&Hu, Bao-Gang.(2015).Unsupervised Ranking of Multi-Attribute Objects Based on Principal Curves.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,27(12),3404-3416.
MLA Li, Chun-Guo,et al."Unsupervised Ranking of Multi-Attribute Objects Based on Principal Curves".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 27.12(2015):3404-3416.
Files in This Item: Download All
File Name/Size DocType Version Access License
Li15.pdf(962KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Chun-Guo]'s Articles
[Mei, Xing]'s Articles
[Hu, Bao-Gang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Chun-Guo]'s Articles
[Mei, Xing]'s Articles
[Hu, Bao-Gang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Chun-Guo]'s Articles
[Mei, Xing]'s Articles
[Hu, Bao-Gang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Li15.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.