CERIASTechReport2001-89.PDFVIP

CERIAS Tech Report 2001-89 Query flocks: a generalization of association-rule mining by Christopher Clifton Center for Education and Research Information Assurance and Security Purdue University, West Lafayette, IN 47907-2086 Query Flocks: A Generalization of Association-Rule Mining* Dick Tsur, Hitachi Corp. Jeffrey D. Ullman, Stanford University Serge Abiteboul, Stanford University and INRIA Chris Clifton, MITRE Corp. RajeevMotwani, Stanford University Svetlozar Nestorov,Stanford University Arnon Rosenthal,MITRE Corp. March 51998 Abstract By expressing the query flock in Datalog, we find a well- known condition (query safety) that lets us enumeratethe Association-rule mining hasproveda highly successfultech- queriesthat are candidatesfor use in a query optimization nique for extracting useful information from very large technique that generalizesa-priori. Interestingly, the same databases. This successis attributed not only to the ap- technique,while applicableto SQL queriesdirectly, is more propriatenessof the objectives, but to the fact that a number apparentif we expressqueriesin Datalog. of newquery-op