Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networks
This work addresses efficiency issues for users of logic-based XAI methods, though it is incremental as it builds on existing techniques.
The paper tackled the high computational cost of logic-based methods for explaining neural network decisions by combining bound propagation with constraint simplification, resulting in up to 89.26% reduction in explanation time, especially for larger networks.
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.