Learning multiple metrics for ranking

doi:10.1007/s11704-011-0152-5

	Learning multiple metrics for ranking
	Geng, Xiubo; Cheng, Xue-Qi
	2011-09-01
发表期刊	FRONTIERS OF COMPUTER SCIENCE IN CHINA
ISSN	1673-7350
卷号	5 期号:3 页码:259-267
摘要	Directly optimizing an information retrieval (IR) metric has become a hot topic in the field of learning to rank. Conventional wisdom believes that it is better to train for the loss function on which will be used for evaluation. But we often observe different results in reality. For example, directly optimizing averaged precision achieves higher performance than directly optimizing precision@3 when the ranking results are evaluated in terms of precision@3. This motivates us to combine multiple metrics in the process of optimizing IR metrics. For simplicity we study learning with two metrics. Since we usually conduct the learning process in a restricted hypothesis space, e.g., linear hypothesis space, it is usually difficult to maximize both metrics at the same time. To tackle this problem, we propose a relaxed approach in this paper. Specifically, we incorporate one metric within the constraint while maximizing the other one. By restricting the feasible hypothesis space, we can get a more robust ranking model. Empirical results on the benchmark data set LETOR show that the relaxed approach is superior to the direct linear combination approach, and also outperforms other baselines.
关键词	learning to rank multiple measures direct optimization
DOI	10.1007/s11704-011-0152-5
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:000293638400001
出版者	HIGHER EDUCATION PRESS
引用统计	被引频次：3[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/2XEOYT63/13234
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Geng, Xiubo
作者单位	Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Geng, Xiubo,Cheng, Xue-Qi. Learning multiple metrics for ranking[J]. FRONTIERS OF COMPUTER SCIENCE IN CHINA,2011,5(3):259-267.
APA	Geng, Xiubo,&Cheng, Xue-Qi.(2011).Learning multiple metrics for ranking.FRONTIERS OF COMPUTER SCIENCE IN CHINA,5(3),259-267.
MLA	Geng, Xiubo,et al."Learning multiple metrics for ranking".FRONTIERS OF COMPUTER SCIENCE IN CHINA 5.3(2011):259-267.