Abstract
We study evaluation of online classifiers that are designed to adapt to changes in data distribution over time (concept drift). A standard procedure to evaluate such classifiers is the test-then-train, which iteratively uses the incoming instances for testing and then for updating a classifier. Comparing classifiers based on such a test risks to give biased results, since a dataset is processed only once in a fixed sequential order. Such a test concludes how well classifiers adapt when changes happen at fixed time points, while the ultimate goal is to assess how well they would adapt when changes of a similar type happen unexpectedly. To reduce the risk of biased evaluation we propose to run multiple tests with permuted data. A random permutation is not suitable, as it makes the data distribution uniform over time and destroys the adaptive learning problem. We develop three permutation techniques with theoretical control mechanisms that ensure that different distributions in data are preserved while perturbing the data order. The idea is to manipulate blocks of data keeping individual instances close together. Our permutations reduce the risk of biased evaluation by making it possible to analyze sensitivity of classifiers to variations in the data order.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aldous, D., Diaconis, P.: Shuffling cards and stopping times. The American Mathematical Monthly 93(5), 333–348 (1986)
Antoch, J., Huskova, M.: Permutation tests in change point analysis. Statistics and Probability Letters 53, 37–46 (2001)
Atkinson, M.: Restricted permutations. Discrete Math. 195, 27–38 (1999)
Bach, S., Maloof, M.: A bayesian approach to concept drift. In: Advances in Neural Information Processing Systems 23 (NIPS), pp. 127–135 (2010)
Baena-Garcia, M., del Campo-Avila, J., Fidalgo, R., Bifet, A., Gavalda, R., Morales-Bueno, R.: Early drift detection method. In: Proc. of ECML/PKDD Workshop on Knowledge Discovery from Data Streams (2006)
Bifet, A., Holmes, G., Kirkby, R., Pfahringer, B.: MOA: Massive Online Analysis. Journal of Machine Learning Research 11, 1601–1604 (2010)
Bifet, A., Holmes, G., Pfahringer, B.: Leveraging bagging for evolving data streams. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS, vol. 6321, pp. 135–150. Springer, Heidelberg (2010)
Bifet, A., Holmes, G., Pfahringer, B., Kirkby, R., Gavalda, R.: New ensemble methods for evolving data streams. In: Proc. of the 15th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD 2009), pp. 139–148 (2009)
Demsar, J.: Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research 7, 1–30 (2006)
Diaconis, P.: Group representations in probability and statistics. Lecture Notes–Monograph Series, vol. 11. Hayward Inst. of Mathematical Statistics (1988)
Dietterich, T.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 10(7), 1895–1923 (1998)
Durrett, R.: Shuffling chromosomes. J. of Theor. Probability 16(3), 725–750 (2003)
Gama, J., Medas, P., Castillo, G., Rodrigues, P.: Learning with drift detection. In: Bazzan, A.L.C., Labidi, S. (eds.) SBIA 2004. LNCS (LNAI), vol. 3171, pp. 286–295. Springer, Heidelberg (2004)
Gama, J., Sebastiao, R., Rodrigues, P.P.: Issues in evaluation of stream learning algorithms. In: Proc. of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2009), pp. 329–338 (2009)
Harries, M.: Splice-2 comparative evaluation: Electricity pricing. Technical report, The University of South Wales (1999)
Ikonomovska, E., Gama, J., Dzeroski, S.: Learning model trees from evolving data streams. Data (2010)
Masud, M., Chen, Q., Khan, L., Aggarwal, C., Gao, J., Han, J., Thuraisingham, B.: Addressing concept-evolution in concept-drifting data streams. In: Proc. of the 10th IEEE Int. Conf. on Data Mining, ICDM 2010 (2010)
Ojala, M., Garriga, G.: Permutation tests for studying classifier performance. Journal of Machine Learning Research 11, 1833–1863 (2010)
Pemantle, R.: Randomization time for the overhand shuffle. J. of Theoretical Probability 2(1), 37–49 (1989)
Pfahringer, B., Holmes, G., Kirkby, R.: New options for hoeffding trees. In: Orgun, M.A., Thornton, J. (eds.) AI 2007. LNCS (LNAI), vol. 4830, pp. 90–99. Springer, Heidelberg (2007)
Politis, D.: The impact of bootstrap methods on time series analysis. Statistical Science 18(2), 219–230 (2003)
Schiavinotto, T., Stutzle, T.: A review of metrics on permutations for search landscape analysis. Computers and Operations Research 34(10), 3143–3153 (2007)
Sorensen, K.: Distance measures based on the edit distance for permutation-type representations. Journal of Heuristics 13(1), 35–47 (2007)
Welch, W.: Construction of permutation tests. Journal of the American Statistical Association 85(411), 693–698 (1990)
Zliobaite, I.: Controlled permutations for testing adaptive classifiers. Technical report (2011), https://sites.google.com/site/zliobaite/permutations
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Žliobaitė, I. (2011). Controlled Permutations for Testing Adaptive Classifiers. In: Elomaa, T., Hollmén, J., Mannila, H. (eds) Discovery Science. DS 2011. Lecture Notes in Computer Science(), vol 6926. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24477-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-24477-3_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24476-6
Online ISBN: 978-3-642-24477-3
eBook Packages: Computer ScienceComputer Science (R0)