Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Luiz Fernando Paulino Queiroz, Carlos Henrique Leitão Cavalcante, Thiago Alves Rocha

TL;DR

This paper proposes an approach leveraging domain slicing to facilitate explanation generation for NNs by reducing the complexity of logical constraints through slicing, which decreases explanation time by up to 40% less, as indicated through comparative experiments.

Abstract

Neural networks (NNs) are pervasive across various domains but often lack interpretability. To address the growing need for explanations, logic-based approaches have been proposed to explain predictions made by NNs, offering correctness guarantees. However, scalability remains a concern in these methods. This paper proposes an approach leveraging domain slicing to facilitate explanation generation for NNs. By reducing the complexity of logical constraints through slicing, we decrease explanation time by up to 40\% less time, as indicated through comparative experiments. Our findings highlight the efficacy of domain slicing in enhancing explanation efficiency for NNs.

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

TL;DR

This paper proposes an approach leveraging domain slicing to facilitate explanation generation for NNs by reducing the complexity of logical constraints through slicing, which decreases explanation time by up to 40% less, as indicated through comparative experiments.

Abstract

Neural networks (NNs) are pervasive across various domains but often lack interpretability. To address the growing need for explanations, logic-based approaches have been proposed to explain predictions made by NNs, offering correctness guarantees. However, scalability remains a concern in these methods. This paper proposes an approach leveraging domain slicing to facilitate explanation generation for NNs. By reducing the complexity of logical constraints through slicing, we decrease explanation time by up to 40\% less time, as indicated through comparative experiments. Our findings highlight the efficacy of domain slicing in enhancing explanation efficiency for NNs.
Paper Structure (7 sections, 3 equations, 1 figure, 1 algorithm)

This paper contains 7 sections, 3 equations, 1 figure, 1 algorithm.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. First-order Logic over LRA
  4. Classification Problems and Neural Networks
  5. MILP – Mixed Integer Linear Programming
  6. Logic-based XAI for Neural Networks
  7. Logic-based XAI for NNs via Slicing

Figures (1)

  • Figure 1: Example of Neural Network

Theorems & Definitions (1)

  • definition thmcounterdefinition: Abductive Explanation ignatiev2019abduction