Advertisement

Pruning Strategies Based on the Upper Bound of Information Gain for Discriminative Subgraph Mining

  • Kouzou Ohara
  • Masahiro Hara
  • Kiyoto Takabayashi
  • Hiroshi Motoda
  • Takashi Washio
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5465)

Abstract

Given a set of graphs with class labels, discriminative subgraphs appearing therein are useful to construct a classification model. A graph mining technique called Chunkingless Graph-Based Induction (Cl-GBI) can find such discriminative subgraphs from graph structured data. But, it sometimes happens that Cl-GBI cannot extract subgraphs that are good enough to characterize the given data due to its time and space complexities. Thus, to improve its efficiency, we propose pruning methods based on the upper-bound of information gain that is used as a criterion for discriminability of subgraphs in Cl-GBI. The upper-bound of information gain of a subgraph is the maximal one that its super graph can achieve. By comparing the upper-bound of each subgraph with the best information gain at the moment, Cl-GBI can exclude unfruitful subgraphs from its search space. Furthermore, we experimentally evaluate the effectiveness of the pruning methods on a real world and artificial datasets.

Keywords

Graph mining information gain discriminative subgraph data mining 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cook, D.J., Holder, L.B.: Substructure discovery using minimum description length and background knowledge. Journal of Artificial Intelligence Research 1, 231–255 (1994)Google Scholar
  2. 2.
    Yoshida, K., Motoda, H.: Clip: Concept learning from inference patterns. Artificial Intelligence 75(1), 63–92 (1995)CrossRefGoogle Scholar
  3. 3.
    Matsuda, T., Motoda, H., Yoshida, T., Washio, T.: Mining patterns from structured data by beam-wise graph-based induction. In: Lange, S., Satoh, K., Smith, C.H. (eds.) DS 2002. LNCS, vol. 2534, pp. 422–429. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Yan, X., Han, J.: gSpan: Graph-based structure pattern mining. In: 2002 IEEE International Conference on Data Mining (ICDM 2002), pp. 721–724 (2002)Google Scholar
  5. 5.
    Inokuchi, A., Washio, T., Motoda, H.: Complete mining of frequent patterns from graphs: Mining graph data. Machine Learning 50(3), 321–354 (2003)CrossRefzbMATHGoogle Scholar
  6. 6.
    Kuramochi, M., Karypis, G.: An efficient algorithm for discovering frequent subgraphs. IEEE Trans. Knowledge and Data Engineering 16(9), 1038–1051 (2004)CrossRefGoogle Scholar
  7. 7.
    Nguyen, P.C., Ohara, K., Motoda, H., Washio, T.: Cl-gbi: A novel approach for extracting typical patterns from graph-structured data. In: Ho, T.-B., Cheung, D., Liu, H. (eds.) PAKDD 2005. LNCS (LNAI), vol. 3518, pp. 639–649. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Quinlan, J.R.: Induction of decision trees. Machine Learning 1, 81–106 (1986)Google Scholar
  9. 9.
    Morishita, S., Sese, j.: Traversing itemset lattices with statical metric pruning. In: 19th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pp. 226–236 (2000)Google Scholar
  10. 10.
    Nguyen, P.C., Ohara, K., Mogi, A., Motoda, H., Washio, T.: Constructing decision trees for graph-structured data by chunkingless graph-based induction. In: Ng, W.-K., Kitsuregawa, M., Li, J., Chang, K. (eds.) PAKDD 2006. LNCS (LNAI), vol. 3918, pp. 390–399. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Geamsakul, W., Yoshida, T., Ohara, K., Motoda, H., Yokoi, H., Takabayashi, K.: Constructing a decision tree for graph-structured data and its applications. Fundamenta Informaticae 66(1-2), 131–160 (2005)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Kouzou Ohara
    • 1
  • Masahiro Hara
    • 1
  • Kiyoto Takabayashi
    • 1
  • Hiroshi Motoda
    • 1
  • Takashi Washio
    • 1
  1. 1.The Institute of Scientific and Industrial ResearchOsaka UniversityOsakaJapan

Personalised recommendations