ParaDualMiner: An Efficient Parallel Implementation of the DualMiner Algorithm

  • Roger M. H. Ting
  • James Bailey
  • Kotagiri Ramamohanarao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3056)


Constraint based mining finds all itemsets that satisfy a set of predicates. Many constraints can be categorised as being either monotone or antimonotone. Dualminer was the first algorithm that could utilise both classes of constraint simultaneously to prune the search space. In this paper, we present two parallel versions of DualMiner. The ParaDualMiner with Simultaneous Pruning efficiently distributes the task of expensive predicate checking among processors with minimum communication overhead. The ParaDualMiner with Random Polling makes further improvements by employing a dynamic subalgebra partitioning scheme and a better communication mechanism. Our experimental results indicate that both algorithms exhibit excellent scalability.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agrawal, R., Shafer, J.C.: Parallel mining of association rules. IEEE Trans. On Knowledge And Data Engineering 8, 962–969 (1996)CrossRefGoogle Scholar
  2. 2.
    Agrawal, R., Srikant, R.: Fast algorithms for mining association rules in large databases. In: Proceedings of VLDB 1994, pp. 487–499 (1994)Google Scholar
  3. 3.
    Bayardo, R., Agrawal, R., Gunopulos, D.: Constraint-based rule mining in large, dense databases. In: Proceedings of ICDE 1999, pp. 188–197 (1999)Google Scholar
  4. 4.
    Bucila, C., Gehrke, J., Kifer, D., White, W.: Dualminer: a dual-pruning algorithm for itemsets with constraints. In: Proceedings of ACM SIGKDD 2002, pp. 42–51 (2002)Google Scholar
  5. 5.
    Burdick, D., Calimlim, M., Gehrke, J.: Mafia: A maximal frequent itemset algorithm for transactional databases. In: Proceedings of ICDE 2001, pp. 443–452 (2001)Google Scholar
  6. 6.
    Eager, D.L., Lazowska, E.D., Zahorjan, J.: A comparison of receiver-initiated and sender-initiated adaptive load sharing. In: Proceedings of ACM SIGMETRICS 1985, pp. 1–3 (1985)Google Scholar
  7. 7.
    Han, E.H., Karypis, G., Kumar, V.: Scalable parallel data mining for association rules. In: Proceedings of SIGMOD 1997, pp. 277–288 (1997)Google Scholar
  8. 8.
    Ng, R.T., Lakshmanan, L.V., Han, J., Pang, A.: Exploratory mining and pruning optimizations of constrained association rules. In: Proceedings of SIGMOD 1998, pp. 13–24 (1998)Google Scholar
  9. 9.
    Orlando, S., Palmerini, P., Perego, R., Silvestri, F.: Adaptive and resource-aware mining of frequent sets. In: Proceedings of ICDM 2002, p. 338 (2002)Google Scholar
  10. 10.
    Pei, J., Han, J., Lakshmanan, L.: Mining frequent item sets with convertible constraints. In: Proceedings of ICDE 2001, pp. 433–442 (2001)Google Scholar
  11. 11.
    Sanders, P.: A detailed analysis of random polling dynamic load balancing. In: Proceedings of ISPAN 1994, pp. 382–389 (1994)Google Scholar
  12. 12.
    Sanders, P.: Asynchronous random polling dynamic load balancing. In: Aggarwal, A.K., Pandu Rangan, C. (eds.) ISAAC 1999. LNCS, vol. 1741, p. 39. Springer, Heidelberg (1999)Google Scholar
  13. 13.
    Raedt, L.D., Kramer, S.: The levelwise version space algorithm and its application to molecular fragment finding. In: Proceedings of IJCAI 2001, pp. 853–8622 (2001)Google Scholar
  14. 14.
    Zaiane, O., El-Hajj, M., Lu, P.: Fast parallel association rule mining without candidacy generation. In: Proceedings of ICDM 2001, pp. 665–668 (2001)Google Scholar
  15. 15.
    Zaki, M., Li, W., Parthasarathy, S.: Customized dynamic load balancing for a network of workstations. Journal of Parallel and Distributed Computing 43(2), 156–162 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Roger M. H. Ting
    • 1
  • James Bailey
    • 1
  • Kotagiri Ramamohanarao
    • 1
  1. 1.Department of Computer Science and Software EngineeringThe University of MelbourneAustralia

Personalised recommendations