@inproceedings{89ed40aebcd24bbd8d48ca59d380b484,
title = "An efficient multi-relational na{\"i}ve Bayesian classifier based on semantic relationship graph",
abstract = "Classification is one of the most popular data mining tasks with a wide range of applications, and lots of algorithms have been proposed to build accurate and scalable classifiers. Most of these algorithms only take a single table as input, whereas in the real world most data are stored in multiple tables and managed by relational database systems. As transferring data from multiple tables into a single one usually causes many problems, development of multi-relational classification algorithms becomes important and attracts many researchers' interests. Existing works about extending Na{\"i}ve Bayes to deal with multi-relational data either have to transform data stored in tables to mainmemory Prolog facts, or limit the search space to only a small subset of real world applications. In this work, we aim at solving these problems and building an efficient, accurate Na{\"i}ve Bayesian classifier to deal with data in multiple tables directly. We propose an algorithm named Graph-NB, which upgrades Na{\"i}ve Bayesian classifier to deal with multiple tables directly. In order to take advantage of linkage relationships among tables, and treat different tables linked to the target table differently, a semantic relationship graph is developed to describe the relationship and to avoid unnecessary joins. Furthermore, to improve accuracy, a pruning strategy is given to simplify the graph to avoid examining too many weakly linked tables. Experimental study on both realworld and synthetic databases shows its high efficiency and good accuracy.",
keywords = "Classification, Data Mining, Na{\"i}ve Bayes",
author = "Hongyan Liu and Xiaoxin Yin and Jiawei Han",
note = "Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant No. 70471006 and 70321001, and by the U.S. National Science Foundation NSF IIS-02-09199 and IIS-03-08215.; 4th International Workshop on Multi-Relational Data Mining, MRDM 2005 ; Conference date: 21-08-2005",
year = "2005",
month = aug,
day = "21",
doi = "10.1145/1090193.1090200",
language = "English (US)",
series = "Proceedings of the 4th International Workshop on Multi-Relational Data Mining, MRDM 2005 - 11th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2005",
publisher = "Association for Computing Machinery",
pages = "39--48",
editor = "Hendrik Blockeel and Saso Dzeroski",
booktitle = "Proceedings of the 4th International Workshop on Multi-Relational Data Mining, MRDM 2005 - 11th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2005",
address = "United States",
}