D. Cheung, J. Han, V. T. Ng, and A. W. Fu an Y. Fu. Fast distributed algorithm for mining association rules. In International Conference on Parallel and Distributed Information Systems, pages 31--42, 1996.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....support the rule, and the total count of all transactions at the site. From this, we can compute the global support of each rule, and (from the lemma) be certain that all rules with support at least k have been found. More thorough studies of distributed association rule mining can be found in [2, 3]. The above approach protects individual data privacy, but it does require that each site disclose what rules it supports, and how much it supports each potential global rule. What if this information is sensitive For example, suppose the Centers for Disease Control (CDC) a public agency, would ....

....association rule mining is to find the sets L (k) for all k 1 and the support counts for these itemsets, and from this compute association rules with the specified minimum support and confidence. A fast algorithms related for distributed association rule mining is given in Cheung et al.[2]. Their procedure for fast distributed mining of association rules (FDM) is summarized below. 1. Candidate Sets Generation: Generate candidate sets CG i(k) based on GL i(k 1) itemsets that are supported by the S i at the (k 1) th iteration, using the classic apriori candidate generation ....

[Article contains additional citation context not shown here]

D. W.-L. Cheung, J. Han, V. Ng, A. W.-C. Fu, and Y. Fu, "A fast distributed algorithm for mining association rules," in Proceedings of the 1996.

....MPR Teltech Ltd. National Research Council of Canada, and Hughes Research Laboratories. automatic generation and adjustment of concept hierarchies [16] mining multi level association rules [15] meta rule guided mining of associations [22] incremental and distributed mining of associations [8, 7], constraint pushing in association mining [10, 27] mining periodicity and similarity in time series data [11, 30] multi level classification and prediction [23, 6] spatial data cube construction [21] spatial association rule mining [24] OLAP mining [12] Weblog mining [31] etc. A data ....

....can be applied to parallel and or distributed mining of association rules so that locally large itemsets can be mined in each partition, and with minimal message passing, one may compute the globally large itemsets without redistributing data to different sites. A detailed study is presented in [7]. 3.3 Constrained association rule mining It is highly desirable to promote ad doc query based data mining since users may like to examine different portions of data with different constraints. Constrained association rule mining is to support constraint based, human centered exploratory mining ....

D.W. Cheung, J. Nan, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc. 1996.

....have that support the rule, and the total count of all items at the site. From this, we can compute the global support of each rule, and (from the lemma) be certain that all rules with support at least k have been found. More thorough studies of distributed association rule mining can be found in [5, 6]. The above approach protects individual data privacy, but it does require that each site disclose what rules it supports, and how much it supports each potential global rule. What if this information is sensitive For example, suppose the Centers for Disease Control (CDC) a public agency, ....

....If a k itemset is locally large at some site S i and is globally large it is referred to as GL i(k) The aim of distributed association rule mining is to find all rules whose global support and global confidence are higher than the user specified minimum support and confidence. The FDM algorithm [5] is a fast method for distributed mining of association rules. We summarize this below: 1. Candidate Set Generation: Intersect the globally large itemsets of size k 1, G (k 1) with locally large k 1 itemsets to get GL i(k 1) From these, use the classic apriori candidate generation ....

[Article contains additional citation context not shown here]

D. W.-L. Cheung, J. Han, V. Ng, A. W.-C. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proceedings of the 1996.

....per node decrease, the producer thread consumes fewer cycles, resulting in more substantial performance gains with the use of the fourth consumer thread. 5 Related Work We now compare our work with related research efforts. Parallelization of association mining techniques is a well studied area [1, 10, 13, 14, 19, 20, 21, 24, 31, 29]. Our work is unique in considering hierarchical parallelism on disk resident datasets, and using a middleware to implement the algorithm without low level parallel programming. Our method for shared memory parallelization is significantly different from the existing parallel association mining ....

....on disk resident datasets, and using a middleware to implement the algorithm without low level parallel programming. Our method for shared memory parallelization is significantly different from the existing parallel association mining algorithms on shared memory and hierarchical systems [10, 20, 21, 31, 29]. Through the use of our middleware, we combine task and data parallelism, and exploit four new techniques for avoiding race conditions while updating candidate counts. One effort somewhat similar to our work is from Becuzzi et al. 3] They use a structured parallel programming environment ....

D. Cheung, J. Han, V. Ng, A. Fu, and Y.Fu. A fast distributed algorithm for mining association rules. In 4th Intl. Conf. Parallel and Distributed Info. Systems, December 1996.

....only two full I O scans for the dataset. Our approach presented in this paper is based on this idea. In spite of the significance of the association rule mining and in particular the generation of frequent itemsets, few advances have been made on parallelizing association rule mining algorithms [6, 2]. Most of the work on parallelizing association rules mining on Sharedmemory MultiProcessor (SMP) architecture was based on apriori like algorithms. Parthasarathy et al. 10] have written an excellent recent survey on parallel association rule mining with sharedmemory architecture covering most ....

D. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc.

....the viability of using data reduction techniques such as discretization, wavelet transforms, and sampling, while sacrificing little in terms of result quality. Simultaneously to compute results faster, researchers are turning to effective parallelization of existing data mining algorithms [19, 23, 3]. Modern day enterprises usually contain a cluster of shared memory workstations connected by some (intraenterprise) network. Such a cluster of shared memory symmetric multi processors (SMPs) can be a cost effective powerful computational resource. However, the performance achieved by parallel ....

....data server(s) to the compute cluster. The number of actual associations in a given association set is completely dependent on the characteristics of the dataset 2 , as well as on the input parameters (minimum support) and is therefore difficult to predict in advance. Distributed versions [3] of the Apriori [1] algorithm that exchange candidate itemsets also exhibit this property. Here, the number of candidate itemsets, and therefore the amount of information communicated, depends on the characteristics of the dataset and input parameters. Bursty Communication: As we see from the ....

D. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. 4th Intl. Conf. Parallel and Distributed Info. Systems, Dec. 1996.

....These two techniques make use of the local support counts of large itemsets found in an iteration to prune candidates for the next iteration. These two pruning techniques have been adopted in a mining algorithm FDM (Fast Distributed Mining) previously proposed by us for distributed databases [7, 8]. However, FDM is not suitable for parallel environment, it requires at least two rounds of message exchanges in each iteration that increases the response time significantly. We have adopted the two pruning techniques to develop a new parallel mining algorithm FPM (Fast Parallel Mining) which ....

....for mining association rules on distributed share nothing parallel system which requires fewer rounds of message communication. An itemset is locally large at a processor if it is large within the partition at the processor. It is globally large if it is large with respect to the whole database [7, 8]. Note that every globally large itemset must be locally large at some processor. Refer to Section 3 for details. More precise definitions of skewness and workload balance will be given in Section 4. 2. We have shown analytically that the performance of the pruning techniques in FPM are very ....

[Article contains additional citation context not shown here]

D. W. Cheung, J. Han, V. T. Ng, A. W. Fu, Y. Fu. A fast distributed algorithm for mining association rules. In Proc. of 4th Int. Conf. on Parallel and Distributed Information Systems, 1996

....from the Networks of Centres of Excellence of Canada, and grants from B.C. Advanced Systems Institute, MPR Teltech Ltd. National Research Council of Canada, and Hughes Research Laboratories. recta rule guided mining of associations [22] incremental and distributed mining of associations [8, 7], constraint pushing in association mining [t0, 27] mining periodicity and similarity in time series data [tt, 30] multi level classification and prediction [23, 6] spatial data cube construction [21] spatial association rule mining [24] OLAP mining [12] Weblog mining [31] etc. A data ....

....can be applied to parallel and or distributed mining of association rules so that locally large itemsets can be mined in each partition, and with minimal message passing, one may compute he globally large iemses wi;hou; redis;ribu;ing da;a ;o differen; si;es. A de;ailed sudy is presented in [7]. 3.3 Constrained association rule mining I; is highly desirable ;o promo;e ad doc query based da;a mining since users may like ;o examine differen; pot;ions of da;a wi;h differen; cons;rain;s. Cons;rained associa;ion rule mining is ;o suppot; cons;rain; based, human cen;ered explora;ory mining ....

D.W. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc. 1996.

No context found.

D. Cheung, J. Han, V. T. Ng, and A. W. Fu an Y. Fu. Fast distributed algorithm for mining association rules. In International Conference on Parallel and Distributed Information Systems, pages 31--42, 1996.

No context found.

D. Cheung, J. Han, V. T. Ng, and A. W. Fu an Y. Fu. Fast distributed algorithm for mining association rules. In International Conference on Parallel and Distributed Information Systems, pages 31--42, 1996.

No context found.

Cheung, D., Han, J., Ng, V. T., & Fu, A. W. (1996). Fast distributed algorithm for mining association rules. Proc. of Intl. Conf. on Parallel and Distributed Information Systems.

No context found.

D. Cheung, J. Han, V. T. Ng, and A. W. Fu. Fast distributed algorithm for mining association rules. In Proc. of Intl. Conf. on Parallel and Distributed Information Systems, 1996.

No context found.

D.W. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc. 1996.

No context found.

D. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc. of 1996.

No context found.

D. W.-L. Cheung, J. Han, V. Ng, A. W.-C. Fu, and Y. Fu, "A fast distributed algorithm for mining association rules," in Proceedings of the 1996.

No context found.

D. W. Cheung, J. Han, V. T. Ng, A. W. Fu, and Y. Fu. A Fast Distributed Algorithm for Mining Association Rules. In Proceedings of 1996.

No context found.

D. Cheung, J. Han, V. Ng, A. Fu, , and Y. Fu. A fast distributed algorithm for mining association rules. In 4th Intl. Conf. Parallel and Distributed Info. Systems, 1996a.

No context found.

D. Cheung, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc. of the 4 Int'l Conference on Parallel and Distributed Systems, pages 31--42, Los Alamitos, USA, December 1996.

No context found.

D. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc. of 1996.

No context found.

D. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proc. of 1996.

No context found.

D. W.-L. Cheung, J. Han, V. Ng, A. W.-C. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. In Proceedings of the 1996.

No context found.

D. Cheung, J. Han, V. Ng, A. Fu, , and Y. Fu. A fast distributed algorithm for mining association rules. In 4 Int'l. Conf. Parallel and Distributed Info. Systems, 1996.

No context found.

Cheung, D., Han, J., Ng, V. T., & Fu, A. W. (1996). Fast distributed algorithm for mining association rules. Proc. of Intl. Conf. on Parallel and Distributed Information Systems.

No context found.

D. Cheung, J. Han, V. T. Ng, and A. W. Fu. Fast distributed algorithm for mining association rules. In Proc. of Intl. Conf. on Parallel and Distributed Information Systems, 1996.

No context found.

D. Cheung, J. Han, V. Ng, A. Fu, and Y. Fu. A fast distributed algorithm for mining association rules. 4th Intl. Conf. Parallel and Distributed Info. Systems, December 1996.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC