Skip to Main content Skip to Navigation
Conference papers

On Efficiently Explaining Graph-Based Classifiers

Abstract : Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper shows that for a wide range of classifiers, globally referred to as decision graphs, and which include decision trees and binary decision diagrams, but also their multi-valued variants, there exist polynomial-time algorithms for computing one PI-explanation. In addition, the paper also proposes a polynomial-time algorithm for computing one contrastive explanation. These novel algorithms build on explanation graphs (XpG's). XpG's denote a graph representation that enables both theoretical and practically efficient computation of explanations for decision graphs. Furthermore, the paper proposes a practically efficient solution for the enumeration of explanations, and studies the complexity of deciding whether a given feature is included in some explanation. For the concrete case of decision trees, the paper shows that the set of all contrastive explanations can be enumerated in polynomial time. Finally, the experimental results validate the practical applicability of the algorithms proposed in the paper on a wide range of publicly available benchmarks.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03311514
Contributor : Xuanxiang Huang Connect in order to contact the contributor
Submitted on : Sunday, August 1, 2021 - 9:27:14 AM
Last modification on : Thursday, September 9, 2021 - 3:16:08 AM

File

paper.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

  • HAL Id : hal-03311514, version 1

Citation

Xuanxiang Huang, Yacine Izza, Alexey Ignatiev, João Marques Silva. On Efficiently Explaining Graph-Based Classifiers. 18th International Conference on Principles of Knowledge Representation and Reasoning (KR 2021), Principles of Knowledge Representation and Reasoning, Incorporated (KR Inc.), Nov 2021, Hanoi (virtual), Vietnam. ⟨hal-03311514⟩

Share

Metrics

Record views

79

Files downloads

23