# Metric Logic Program Explanations for Complex Separator Functions

## 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.

## Keywords

Support Vector Machine Association Rule Logic Program Past Work Predicate Symbol## Notes

### Acknowledgements

Parts of this work were supported by ONR grant N000141612739 and ARO grant W911NF1610342.

## References

- 1.Online appendix (2016). https://sites.google.com/site/mlpextraction/
- 2.Agrawal, R., Imieliński, T., Swami, A.: Mining association rules between sets of items in large databases. SIGMOD Rec.
**22**(2), 207–216 (1993)CrossRefGoogle Scholar - 3.Barakat, N.H., Bradley, A.P.: Rule extraction from support vector machines: a review. Neurocomputing
**74**(1–3), 178–190 (2010)CrossRefGoogle Scholar - 4.Beldiceanu, N., Carlsson, M., Flener, P., Pearson, J.: On the reification of global constraints. Constraints
**18**(1), 1–6 (2013)MathSciNetCrossRefzbMATHGoogle Scholar - 5.Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth and Brooks, Monterey (1984)zbMATHGoogle Scholar
- 6.Cohen, W.W.: Fast effective rule induction. In: ICML, pp. 115–123 (1995)Google Scholar
- 7.Craven, M.W., Shavlik, J.W.: Extracting tree-structured representations of trained networks. Adv. Neural Inf. Process. Syst.
**8**, 24–30 (1996)Google Scholar - 8.Diederich, J. (ed.): Rule Extraction from Support Vector Machines. Studies in Computational Intelligence, vol. 80. Springer, Heidelberg (2008)zbMATHGoogle Scholar
- 9.Dyer, M.E., Frieze, A.M.: On the complexity of computing the volume of a polyhedron. SIAM J. Comput.
**17**(5), 967–974 (1988)MathSciNetCrossRefzbMATHGoogle Scholar - 10.Eiter, T., Gottlob, G.: The complexity of logic-based abduction. J. ACM (JACM)
**42**(1), 3–42 (1995)MathSciNetCrossRefzbMATHGoogle Scholar - 11.Jaffar, J., Lassez, J.-L.: Constraint logic programming. In: POPL, pp. 111–119 (1987)Google Scholar
- 12.Kakas, A.C., Michael, A., Mourlas, C.: ACLP: abductive constraint logic programming. J. Log. Program.
**44**(1), 129–177 (2000)MathSciNetCrossRefzbMATHGoogle Scholar - 13.Lloyd, J.W.: Foundations of Logic Programming. Springer, New York (1987)CrossRefzbMATHGoogle Scholar
- 14.Martens, D., Baesens, B., Van Gestel, T.: Decompositional rule extraction from support vector machines by active learning. IEEE Trans. Knowl. Data Eng.
**21**(2), 178–191 (2009)CrossRefGoogle Scholar - 15.Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers Inc., Los Altos (1993)Google Scholar
- 16.Reiter, R.: On closed world data bases. In: Ginsberg, M.L. (ed.) Readings in Nonmonotonic Reasoning, pp. 300–310. Kaufmann, Los Altos (1987)Google Scholar
- 17.Schmitz, G.P., Aldrich, C., Gouws, F.S.: ANN-DT: an algorithm for extraction of decision trees from artificial neural networks. IEEE Trans. Neural Netw.
**10**(6), 1392–1401 (1999)CrossRefGoogle Scholar - 18.Zhu, P., Qinghua, H.: Rule extraction from support vector machines based on consistent region covering reduction. Knowl. Based Syst.
**42**, 1–8 (2013)CrossRefGoogle Scholar