A fast distributed algorithm for mining association rules

Conference · Tue Dec 31 04:00:00 EST 1996

OSTI ID:535540

Cheung, D W ^[1]; Fu, A W ^[2]; Ng, V T ^[3]

---

1. Univ. of Hong Kong (Hong Kong)
2. Chinese Univ. of Hong Kong (Hong Kong)
3. Hong Kong Polytechnic Univ. (Hong Kong); and others

With the existence of many large transaction databases, the huge amounts of data, the high scalability of distributed systems, and the easy partition and distribution of a centralized database, it is important to investigate efficient methods for distributed mining of association rules. This study discloses some interesting relationships between locally large and globally large itemsets and proposes an interesting distributed association rule mining algorithm, FDM (Fast Distributed Mining of association rules), which generates a small number of candidate sets and substantially reduces the number of messages to be passed at mining association rules. Our performance study shows that FDM has a superior performance over the direct application of a typical sequential algorithm Further performance enhancement leads to a few variations of the algorithm.

• OSTI ID: 535540
• Report Number(s): CONF-961209--; CNN: Grant 338/065/0026; Grant NSERC-A3723; Grant NCE:IRIS/PRECARN-HMI5
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
ALGORITHMS
DATA BASE MANAGEMENT
DISTRIBUTED DATA PROCESSING
INFORMATION RETRIEVAL
PERFORMANCE