Scaling the Explanation of Multi-Class Bayesian Network Classifiers
This work addresses the need for efficient and scalable explanation methods in machine learning, particularly for multi-class Bayesian network classifiers, though it appears incremental as it builds on prior work focused on binary classifiers.
The authors tackled the problem of explaining multi-class Bayesian network classifiers by proposing a new algorithm that compiles them into class formulas, resulting in significant improvements in compilation time and enabling the generation of OR-decomposable NNF circuits.
We propose a new algorithm for compiling Bayesian network classifier (BNC) into class formulas. Class formulas are logical formulas that represent a classifier's input-output behavior, and are crucial in the recent line of work that uses logical reasoning to explain the decisions made by classifiers. Compared to prior work on compiling class formulas of BNCs, our proposed algorithm is not restricted to binary classifiers, shows significant improvement in compilation time, and outputs class formulas as negation normal form (NNF) circuits that are OR-decomposable, which is an important property when computing explanations of classifiers.