Not Logged In

Visual Explanation and Auditing of Evidence with Additive Classifiers

Full Text: 2006-Paper-Szafron-Proteome_Analyst-IAAI.pdf PDF

Machine-learned classifiers are important components of many data mining and knowledge discovery systems. In several application domains, an explanation of the classifier's reasoning is critical for the classifier’s acceptance by the end-user. We describe a framework, ExplainD, for explaining decisions made by classifiers that use additive evidence. ExplainD applies to many widely used classifiers, including linear discriminants and many additive models. We demonstrate our ExplainD framework using implementations of naïve Bayes, linear support vector machine, and logistic regression classifiers on example applications. ExplainD uses a simple graphical explanation of the classification process to provide visualizations of the classifier decisions, visualization of the evidence for those decisions, the capability to speculate on the effect of changes to the data, and the capability, wherever possible, to drill down and audit the source of the evidence. We demonstrate the effectiveness of ExplainD in the context of a deployed web-based system (Proteome Analyst) and using a downloadable Python-based implementation.

Citation

D. Szafron, B. Poulin, R. Eisner, P. Lu, R. Greiner, D. Wishart, A. Fyshe, B. Pearcy, C. Macdonell, J. Anvik. "Visual Explanation and Auditing of Evidence with Additive Classifiers". Innovative Applications of Artificial Intelligence, July 2006.

Keywords: explanation, linear model, additive models, naive bayes, Proteome Analyst, machine learning, bioinformatics
Category: In Conference

BibTeX

@incollection{Szafron+al:IAAI06,
  author = {Duane Szafron and Brett Poulin and Roman Eisner and Paul Lu and
    Russ Greiner and David S. Wishart and Alona Fyshe and Brandon Pearcy and
    Cam Macdonell and John Anvik},
  title = {Visual Explanation and Auditing of Evidence with Additive
    Classifiers},
  booktitle = {Innovative Applications of Artificial Intelligence},
  year = 2006,
}

Last Updated: October 25, 2007
Submitted by Russ Greiner

University of Alberta Logo AICML Logo