Comparing Neural Network Encodings for Logic-based Explainability

Levi Cordeiro Carvalho, Saulo A. F. Oliveira, Thiago Alves Rocha
5/26/2025
cs.LOcs.AIcs.LG

No confident code implementation found for this paper.

Abstract

Providing explanations for the outputs of artificial neural networks (ANNs) is crucial in many contexts, such as critical systems, data protection laws and handling adversarial examples. Logic-based methods can offer explanations with correctness guarantees, but face scalability challenges. Due to these issues, it is necessary to compare different encodings of ANNs into logical constraints, which are used in logic-based explainability. This work compares two encodings of ANNs: one has been used in the literature to provide explanations, while the other will be adapted for our context of explainability. Additionally, the second encoding uses fewer variables and constraints, thus, potentially enhancing efficiency. Experiments showed similar running times for computing explanations, but the adapted encoding performed up to 18\% better in building logical constraints and up to 16\% better in overall time.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing

84% match2026

Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networks

83% match2026

On Evaluating Explanation Utility for Human-AI Decision Making in NLP

81% match1 repo12024

Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementation

81% match2024

A Survey on Explainability of Graph Neural Networks

81% match2023

xDNN(ASP): Explanation Generation System for Deep Neural Networks powered by Answer Set Programming

81% match2026

Cite this paper

@article{carvalho2025comparing,
  title  = {Comparing Neural Network Encodings for Logic-based Explainability},
  author = {Levi Cordeiro Carvalho and Saulo A. F. Oliveira and Thiago Alves Rocha},
  year   = {2025},
  eprint = {2505.20269},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.20269v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.20269.svg)](https://codeofpaper.com/paper/2505.20269)

Discussion