Advertisement

Comparing Apples and Oranges

Measuring Differences between Data Mining Results
  • Nikolaj Tatti
  • Jilles Vreeken
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6913)

Abstract

Deciding whether the results of two different mining algorithms provide significantly different information is an important open problem in exploratory data mining. Whether the goal is to select the most informative result for analysis, or decide which mining approach will likely provide the most novel insight, it is essential that we can tell how different the information is that two results provide.

In this paper we take a first step towards comparing exploratory results on binary data. We propose to meaningfully convert results into sets of noisy tiles, and compare between these sets by Maximum Entropy modelling and Kullback-Leibler divergence. The measure we construct this way is flexible, and allows us to naturally include background knowledge, such that differences in results can be measured from the perspective of what a user already knows. Furthermore, adding to its interpretability, it coincides with Jaccard dissimilarity when we only consider exact tiles.

Our approach provides a means to study and tell differences between results of different data mining methods. As an application, we show that it can also be used to identify which parts of results best redescribe other results. Experimental evaluation shows our measure gives meaningful results, correctly identifies methods that are similar in nature, and automatically provides sound redescriptions of results.

Keywords

Background Knowledge Maximum Entropy Frequent Itemsets Data Mining Method Maximum Entropy Principle 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Aggarwal, C.C., Wolf, J.L., Yu, P.S., Procopiuc, C., Park, J.S.: Fast algorithms for projected clustering. In: Proc. ACM SIGMOD 1999, pp. 61–72. ACM, New York (1999)CrossRefGoogle Scholar
  2. 2.
    Cover, T.M., Thomas, J.A.: Elements of Information Theory, 2nd edn (2006)Google Scholar
  3. 3.
    Csiszár, I.: I-divergence geometry of probability distributions and minimization problems. Ann. Prob. 3(1), 146–158 (1975)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Darroch, J., Ratcliff, D.: Generalized iterative scaling for log-linear models. Ann. Math. Stat. 43(5), 1470–1480 (1972)CrossRefzbMATHMathSciNetGoogle Scholar
  5. 5.
    De Bie, T.: Maximum entropy models and subjective interestingness: an application to tiles in binary databases. Data Min. Knowl. Disc. (2010)Google Scholar
  6. 6.
    Fortelius, M., Gionis, A., Jernvall, J., Mannila, H.: Spectral ordering and biochronology of european fossil mammals. Paleobiology 32(2), 206–214 (2006)CrossRefGoogle Scholar
  7. 7.
    Gallo, A., Miettinen, P., Mannila, H.: Finding subgroups having several descriptions: Algorithms for redescription mining. In: SDM 2008 (2008)Google Scholar
  8. 8.
    Geerts, F., Goethals, B., Mielikäinen, T.: Tiling databases. In: Suzuki, E., Arikawa, S. (eds.) DS 2004. LNCS (LNAI), vol. 3245, pp. 278–289. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Gionis, A., Mannila, H., Seppänen, J.K.: Geometric and combinatorial tiles in 0-1 data. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) PKDD 2004. LNCS (LNAI), vol. 3202, pp. 173–184. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Hanhijärvi, S., Ojala, M., Vuokko, N., Puolamäki, K., Tatti, N., Mannila, H.: Tell me something I don’t know: randomization strategies for iterative data mining. In: Proc. KDD 2009, pp. 379–388 (2009)Google Scholar
  11. 11.
    Hollmén, J., Seppänen, J.K., Mannila, H.: Mixture models and frequent sets: combining global and local methods for 0-1 data. In: Proc. SDM 2003 (2003)Google Scholar
  12. 12.
    Mampaey, M., Tatti, N., Vreeken, J.: Tell me what I need to know: succinctly summarizing data with itemsets. In: Proc. KDD 2011 (2011)Google Scholar
  13. 13.
    Mampaey, M., Vreeken, J.: Summarising data by clustering items. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS, vol. 6322, pp. 321–336. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  14. 14.
    Miettinen, P., Mielikäinen, T., Gionis, A., Das, G., Mannila, H.: The discrete basis problem. IEEE Trans. Knowl. Data Eng. 20(10), 1348–1362 (2008)CrossRefGoogle Scholar
  15. 15.
    Mitchell-Jones, A.J., Amori, G., Bogdanowicz, W., Krystufek, B., Reijnders, P.J.H., Spitzenberger, F., Stubbe, M., Thissen, J.B.M., Vohralik, V., Zima, J.: The Atlas of European Mammals. Academic Press, London (1999)Google Scholar
  16. 16.
    Müller, E., Günnemann, S., Assent, I., Seidl, T.: Evaluating clustering in subspace projections of high dimensional data. In: Proc. VLDB 2009 (2009)Google Scholar
  17. 17.
    Myllykangas, S., Himberg, J., Böhling, T., Nagy, B., Hollmén, J., Knuutila, S.: DNA copy number amplification profiling of human neoplasms. Oncogene 25(55), 7324–7332 (2006)CrossRefGoogle Scholar
  18. 18.
    Pensa, R., Robardet, C., Boulicaut, J.-F.: A bi-clustering framework for categorical data. In: Jorge, A.M., Torgo, L., Brazdil, P.B., Camacho, R., Gama, J. (eds.) PKDD 2005. LNCS (LNAI), vol. 3721, pp. 643–650. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  19. 19.
    Puolamäki, K., Hanhijärvi, S., Garriga, G.C.: An approximation ratio for biclustering. Inf. Process. Lett. 108(2), 45–49 (2008)CrossRefzbMATHMathSciNetGoogle Scholar
  20. 20.
    Ramakrishnan, N., Kumar, D., Mishra, B., Potts, M., Helm, R.F.: Turning cartwheels: an alternating algorithm for mining redescriptions. In: Proc. KDD 2004, pp. 266–275 (2004)Google Scholar
  21. 21.
    Rasch, G.: Probabilistic Models for Some Intelligence and Attainnment Tests. Danmarks paedagogiske Institut (1960)Google Scholar
  22. 22.
    Tatti, N.: Computational complexity of queries based on itemsets. Inf. Process. Lett., 183–187 (2006)Google Scholar
  23. 23.
    Tatti, N.: Distances between data sets based on summary statistics. J. Mach. Learn. Res. 8, 131–154 (2007)zbMATHMathSciNetGoogle Scholar
  24. 24.
    Tatti, N., Vreeken, J.: Comparing apples and oranges - measuring differences between exploratory data mining results. Technical Report 2011/03, University of Antwerp (2011)Google Scholar
  25. 25.
    Vreeken, J., van Leeuwen, M., Siebes, A.: Characterising the difference. In: Proc. KDD 2007, pp. 765–774 (2007)Google Scholar
  26. 26.
    Vreeken, J., van Leeuwen, M., Siebes, A.: Krimp: Mining itemsets that compress. Data Min. Knowl. Disc. 23(1), 169–214 (2010)CrossRefzbMATHMathSciNetGoogle Scholar
  27. 27.
    Wang, C., Parthasarathy, S.: Summarizing itemset patterns using probabilistic models. In: Proc. KDD 2006, pp. 730–735 (2006)Google Scholar
  28. 28.
    Xiang, Y., Jin, R., Fuhry, D., Dragan, F.: Summarizing transactional databases with overlapped hyperrectangles. Data Min. Knowl. Disc. (2010)Google Scholar
  29. 29.
    Zaki, M.J., Ramakrishnan, N.: Reasoning about sets using redescription mining. In: Proc. KDD 2005, pp. 364–373 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Nikolaj Tatti
    • 1
  • Jilles Vreeken
    • 1
  1. 1.Advanced Database Research and ModelingUniversiteit AntwerpenBelgium

Personalised recommendations