Efficient parallel data mining for association rules
CIKM '95 Proceedings of the fourth international conference on Information and knowledge management
Scalable parallel data mining for association rules
SIGMOD '97 Proceedings of the 1997 ACM SIGMOD international conference on Management of data
Asynchronous parallel algorithm for mining association rules on a shared-memory multi-processors
Proceedings of the tenth annual ACM symposium on Parallel algorithms and architectures
Parallel data mining for association rules on shared-memory multi-processors
Supercomputing '96 Proceedings of the 1996 ACM/IEEE conference on Supercomputing
Communication-efficient distributed mining of association rules
SIGMOD '01 Proceedings of the 2001 ACM SIGMOD international conference on Management of data
A fast distributed algorithm for mining association rules
DIS '96 Proceedings of the fourth international conference on on Parallel and distributed information systems
Parallel Mining of Association Rules
IEEE Transactions on Knowledge and Data Engineering
Fast Parallel Association Rule Mining without Candidacy Generation
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Effect of Data Skewness in Parallel Mining of Association Rules
PAKDD '98 Proceedings of the Second Pacific-Asia Conference on Research and Development in Knowledge Discovery and Data Mining
Parallel FP-growth on PC cluster
PAKDD'03 Proceedings of the 7th Pacific-Asia conference on Advances in knowledge discovery and data mining
High performance evaluation of evolutionary-mined association rules on GPUs
The Journal of Supercomputing
Hi-index | 0.00 |
Parallel association rules mining is a high performance mining method. Until now there are many parallel algorithms to mine association rules, this paper emphatically analyses existing parallel mining algorithms' realization skill and defects. On the basis, a new data structure, called FP-Forest, is designed with a multi-trees structure to store data. At the same time, a new parallel mining model is proposed according to the property of FP-Forest, which combines the advantage of data-parallel method and task-parallel method. First, database is reasonably divided to data processing nodes by core processor, and FP-Forest structure is built on data processing nodes for each sub-database. Secondly, core node perform a one-time synchronization merging for each FP-Forest, and every MFP-Tree on FP-Forest is dynamical assigned to corresponding mining node as sub-task by task-parallel technique. Furthermore, a fast parallel mining algorithm, namely F-FDPM, is presented to mine association rules according to above model, which mining process adopts frequent growth method basing on deepth-first searching strategy. From experimentation on real data sets, the algorithm has greatly enhanced association rules mining efficiency.