arXiv Open Access 2026

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

Ronaldo Gomes Jairo Ribeiro Luiz Queiroz Thiago Alves Rocha

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.LO cs.LG

Penulis (4)

Ronaldo Gomes

Jairo Ribeiro

Luiz Queiroz

Thiago Alves Rocha

Format Sitasi

APA MLA BibTeX

Gomes, R., Ribeiro, J., Queiroz, L., Rocha, T.A. (2026). Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networks. https://arxiv.org/abs/2603.01923

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2026
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓