Link Mining: Models, Algorithms, and Applications: Models, Algorithms, and Applications (Google eBook)
Springer Science & Business Media, Sep 16, 2010 - Computers - 600 pages
This book presents in-depth surveys and systematic discussions on models, algorithms and applications for link mining. Link mining is an important field of data mining. Traditional data mining focuses on 'flat' data in which each data object is represented as a fixed-length attribute vector. However, many real-world data sets are much richer in structure, involving objects of multiple types that are related to each other. Hence, recently link mining has become an emerging field of data mining, which has a high impact in various important applications such as text mining, social network analysis, collaborative filtering, and bioinformatics. At present, there are no books in the market focusing on the theory and techniques as well as the related applications for link mining. On the other hand, due to the high popularity of linkage data, extensive applications ranging from governmental organizations to commercial businesses to people’s daily life call for exploring the techniques of mining linkage data; people need such a reference book to systematically apply the link mining techniques to these applications to develop the related technologies. Therefore, such a book is in high demand on the market.
Part II Graph Mining and Community Analysis
Part III Link Analysis for Data Cleaning and Information Integration
Part IV Social Network Analysis
adjacency matrix algorithm analysis anonymization applications approach attributes authors average bipartite graph citation classification clustering community identification community structure compression compute correlated corresponding cost Data Mining data set database DBLP defined degree sequence denote dimensionality distribution dynamic edges efficient entity resolution evaluation example Faloutsos feature subset Flickr function gene giant component graph data graph mining graph partitioning GraphScope heterogeneous individuals inference information network input interactions International Conference iteration label leaf nodes link mining linkages LinkClus Machine Learning Markov logic Markov network matrix measure methods min_sup modules OLAP optimal original graph PageRank papers parameter partition patterns probability problem proposed random ranking reducible subspace relational data relationships represent score Section similarity SimRank SimTree social networks spectral clustering Springer Science+Business Media step subgraph summarization Supergraph supernodes target objects TS-Rank tuples types update users vector vertex vertices weights