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

2026-03-02 · Ronaldo Gomes, Jairo Ribeiro, Luiz Queiroz, Thiago Alves Rocha arxiv

Logic-based methods for explaining neural network decisions offer formal guarantees of correctness and non-redundancy, but they often suffer from high computational costs, especially for large networks. In this work, we improve the efficiency of such methods by combining bound propagation with constraint simplification. These simplifications, derived from the propagation, tighten neuron bounds and eliminate unnecessary binary variables, making the explanation process more efficient. Our experiments suggest that combining these techniques reduces explanation time by up to 89.26\%, particularly for larger neural networks.

📄 PDF Abstract BibTeX arXiv:2603.01923

Code (0)

등록된 구현이 없습니다.

Boolean Equi-propagation for Concise and Efficient SAT Encodings of Combinatorial Problems

2014-02-04 · Amit Metodi, Michael Codish, Peter James Stuckey

We present an approach to propagation-based SAT encoding of combinatorial problems, Boolean equi-propagation, where constraints are modeled as Boolean functions which propagate information about equalities between Boolea…

Investigating the Scalability and Biological Plausibility of the Activation Relaxation Algorithm

2020-10-13 · Beren Millidge, Alexander Tschantz, Anil Seth, Christopher L Buckley

The recently proposed Activation Relaxation (AR) algorithm provides a simple and robust approach for approximating the backpropagation of error algorithm using only local learning rules. Unlike competing schemes, it conv…

Bound-Founded Semantics for Answer Set Programming with Difference Constraints: Preliminary Report

2026-07-23 · Pedro Cabalar, Jorge Fandinno, Nicolas Rühling, Torsten Schaub 외 arxiv

While the integration of linear constraints has significantly expanded the reach of Answer Set Programming (ASP), existing hybrid solvers often rely on disparate semantic underpinnings that lack a unified logical foundat…

Topological Expressivity of ReLU Neural Networks

2023-10-17 · Ekin Ergen, Moritz Grillo

We study the expressivity of ReLU neural networks in the setting of a binary classification problem from a topological perspective. Recently, empirical studies showed that neural networks operate by changing topology, tr…

Binary Classification

Learning from Scratch: Structurally-masked Transformer for Next Generation Lib-free Simulation

2025-07-23 · Junlang Huang, Hao Chen, Zhong Guan arxiv

This paper proposes a neural framework for power and timing prediction of multi-stage data path, distinguishing itself from traditional lib-based analytical methods dependent on driver characterization and load simplific…