On Translations between ML Models for XAI Purposes

Alexis de Colnet; Pierre Marquis

IJCAI 2023poster3 citations

On Translations between ML Models for XAI Purposes

Abstract

In this paper, the succinctness of various ML models is studied. To be more precise, the existence of polynomial-time and polynomial-space translations between representation languages for classifiers is investigated. The languages that are considered include decision trees, random forests, several types of boosted trees, binary neural networks, Boolean multilayer perceptrons, and various logical representations of binary classifiers. We provide a complete map indicating for every pair of languages C, C' whether or not a polynomial-time / polynomial-space translation exists from C to C'. We also explain how to take advantage of the resulting map for XAI purposes.

Knowledge Representation and Reasoning: KRR: Knowledge compilationKnowledge Representation and Reasoning: KRR: Knowledge representation languages

BibTeX

@inproceedings{ijcai2023p352,
  title     = {On Translations between ML Models for XAI Purposes},
  author    = {de Colnet, Alexis and Marquis, Pierre},
  booktitle = {Proceedings of the Thirty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-23}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Edith Elkind},
  pages     = {3158--3166},
  year      = {2023},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2023/352},
  url       = {https://doi.org/10.24963/ijcai.2023/352},
}