Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks

2026-09-12

AI Summary

本文提出了一种基于神经元激活的符号框架，使用SMT求解器等逻辑引擎有效计算深度神经网络行为的解释，解决了现有技术无法处理深层架构的问题。

Abstract

Formal explainability of classifying neural networks (NNs) is an active area of research, providing explanations with provable guarantees of the classification within continuous regions of the input feature space. However, the existing techniques are either limited to individual input features without guarantees on their relations or the provided solutions fail to scale to deep architectures. This paper addresses these issues by introducing a flexible symbolic framework for an efficient, guided computation of explanations of the NN behavior, parametrized by the activations of internal neurons, and using logical engines such as SMT solvers. Unlike prior methods that rely on specialized NN verifiers, our method yields explanations that are not restricted in shape. Our algorithm is implementable on top of a general-purpose logical solver, isolating the NN-specific encoding from the algorithmic framework. We experimented with a wide range of benchmarks from the domains of image recognition and medicine, illustrating the advantages of the new method, particularly in computational efficiency. Notably, our approach enables logical explanation of deep networks not amenable to prior logic-based methods.

Problem

• neural networks
• formal explainability
• deep architectures

Innovation

• Neuron Activation
• Logical Explanations
• Deep Neural Networks
• SMT Solvers
• Computational Efficiency