Discounted expert weighting for concept drift

Gregory Ditzler, Gail Rosen, Robi Polikar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

Multiple expert systems (MES) have been widely used in machine learning because of their inherent ability to decrease variance and improve generalization performance by receiving advice from more than one expert. However, a typical MES explicitly assumes that training and testing data are independent and identically distributed (iid), which, unfortunately, is often violated in practice when the probability distribution generating the data changes with time. One of the key aspects of any MES algorithm deployed in such environments is the decision rule used to combine the decisions of the experts. Many MES algorithms choose adaptive weighting schemes that adjust the weights of a classifier based on its loss in recent time, or use an average of the experts probabilities. However, in a stochastic setting where the loss of an expert is uncertain at a future point in time, which combiner method is the most reliable? In this work, we show that non-uniform weighting experts can provide a stable upper bound on loss compared to techniques such as a follow-the-Ieader or uniform methodology. Several well-studied MES approaches are tested on a variety of real-world data sets to support and demonstrate the theory.

Original languageEnglish (US)
Title of host publicationProceedings of the 2013 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments, CIDUE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages61-67
Number of pages7
DOIs
StatePublished - Oct 10 2013
Externally publishedYes
Event2013 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments, CIDUE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore, Singapore
Duration: Apr 16 2013Apr 19 2013

Publication series

NameProceedings of the 2013 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments, CIDUE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

Conference

Conference2013 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments, CIDUE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
CountrySingapore
CitySingapore
Period4/16/134/19/13

Keywords

  • concept drift
  • multiple expert systems
  • nonstationary environments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics

Fingerprint Dive into the research topics of 'Discounted expert weighting for concept drift'. Together they form a unique fingerprint.

  • Cite this

    Ditzler, G., Rosen, G., & Polikar, R. (2013). Discounted expert weighting for concept drift. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments, CIDUE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 61-67). [6595773] (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments, CIDUE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013). https://doi.org/10.1109/CIDUE.2013.6595773