Skip to main content
Contribution to Book
Metric Logic Program Explanations for Complex Separator Functions
Scalable Uncertainty Management: 10th International Conference, SUM 2016, Nice, France, September 21-23, 2016, Proceedings
  • Srijan Kumar, University of Maryland
  • Edoardo Serra, Boise State University
  • Francesca Spezzano, Boise State University
  • V. S. Subrahmanian, University of Maryland
Document Type
Conference Proceeding
Publication Date
1-1-2016
Disciplines
Abstract

There are many classifiers that treat entities to be classified as points in a high-dimensional vector space and then compute a separator S between entities in class +1 from those in class -1. However, such classifiers are usually very hard to explain in plain English to domain experts. We propose Metric Logic Programs (MLPs) which are a fragment of constraint logic programs as a new paradigm for explaining S. We present multiple measures of quality of an MLP and define the problem of finding an MLP-Explanation of S and show that it - and various related problems - are NP-hard. We present the MLP_Extract algorithm to extract MLP explanations for S. We show that while our algorithms provide more succinct, simpler, and higher fidelity explanations than association rules that are less expressive, our algorithms do require additional run-time.

Citation Information
Srijan Kumar, Edoardo Serra, Francesca Spezzano and V. S. Subrahmanian. "Metric Logic Program Explanations for Complex Separator Functions" Scalable Uncertainty Management: 10th International Conference, SUM 2016, Nice, France, September 21-23, 2016, Proceedings (2016)
Available at: http://works.bepress.com/francesca_spezzano/6/