mlsanityData to 14 Oct 2026

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

arXiv 2603.01923 ↗First posted 2 Mar 2026cs.LO cs.LGcited by 1

Not on the map. Why?

Abstract (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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

14 of 23 references.

References · 14

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  2. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  3. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 228
  4. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
  5. 2018Abduction-Based Explanations for Machine Learning Modelscited by 160
  6. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 131
  7. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 103
  8. 2021On Explaining Random Forests with SATcited by 57
  9. 2020Robust and Stable Black Box Explanationscited by 47
  10. 2022Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networkscited by 42
  11. 2021Probabilistic Sufficient Explanationscited by 24
  12. 2022Computing Abductive Explanations for Boosted Treescited by 23
2 more
  1. 2023On the Robustness of Removal-Based Feature Attributionscited by 19
  2. 2024Logic-based Explanations for Linear Support Vector Classifiers with Reject Optioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Modelscited by 0