Efficient Computation of Shap Explanation Scores for Neural Network Classifiers via Knowledge Compilation
LOGICS IN ARTIFICIAL INTELLIGENCE, JELIA 2023(2023)
摘要
The use of Shap scores has become widespread in Explainable AI. However, their computation is in general intractable, in particular when done with a black-box classifier, such as neural network. Recent research has unveiled classes of open-box Boolean Circuit classifiers for which Shap can be computed efficiently. We show how to transform binary neural networks into those circuits for efficient Shap computation. We use logic-based knowledge compilation techniques. The performance gain is huge, as we show in the light of our experiments.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要