a general framework to encode heterogeneous information sources for contextual pattern mining

ISCAS OpenIR

	a general framework to encode heterogeneous information sources for contextual pattern mining
	Dong Weishan; Fan Wei; Shi Leib; Zhou Changjin; Yan Xifeng
	2012
会议名称	21st ACM International Conference on Information and Knowledge Management, CIKM 2012
会议录名称	ACM International Conference Proceeding Series
页码	65-74
会议日期	October 29, 2012 - November 2, 2012
会议地点	Maui, HI, United states
收录类别	EI
ISBN	9781450311564
部门归属	(1) IBM Research China; (2) Huawei Noah's Ark Lab. China; (3) Institute of Software Chinese Academy of Sciences China; (4) University of California Santa Barbara CA United States
摘要	Traditional pattern mining methods usually work on single data sources. However, in practice, there are often multiple and heterogeneous information sources. They collectively provide contextual information not available in any single source alone describing the same set of objects, and are useful for discovering hidden contextual patterns. One important challenge is to provide a general methodology to mine contextual patterns easily and efficiently. In this paper, we propose a general framework to encode contextual information from multiple sources into a coherent representation - -Contextual Information Graph (CIG). The complexity of the encoding scheme is linear in both time and space. More importantly, CIG can be handled by any single-source pattern mining algorithms that accept taxonomies without any modification. We demonstrate by three applications of the contextual association rule, sequence and graph mining, that contextual patterns providing rich and insightful knowledge can be easily discovered by the proposed framework. It enables Contextual Pattern Mining (CPM) by reusing single-source methods, and is easy to deploy and use in real-world systems. © 2012 ACM.; Traditional pattern mining methods usually work on single data sources. However, in practice, there are often multiple and heterogeneous information sources. They collectively provide contextual information not available in any single source alone describing the same set of objects, and are useful for discovering hidden contextual patterns. One important challenge is to provide a general methodology to mine contextual patterns easily and efficiently. In this paper, we propose a general framework to encode contextual information from multiple sources into a coherent representation - -Contextual Information Graph (CIG). The complexity of the encoding scheme is linear in both time and space. More importantly, CIG can be handled by any single-source pattern mining algorithms that accept taxonomies without any modification. We demonstrate by three applications of the contextual association rule, sequence and graph mining, that contextual patterns providing rich and insightful knowledge can be easily discovered by the proposed framework. It enables Contextual Pattern Mining (CPM) by reusing single-source methods, and is easy to deploy and use in real-world systems. © 2012 ACM.
关键词	Algorithms Data Mining Knowledge Management
主办者	Special Interest Group on Information Retrieval (ACM SIGIR); ACM SIGWEB
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/15824
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Dong Weishan,Fan Wei,Shi Leib,et al. a general framework to encode heterogeneous information sources for contextual pattern mining[C],2012:65-74.