Efficient Search for Diverse Coherent Explanations
This addresses the need for interpretable and reliable explanations in machine learning models, particularly for complex data structures, though it appears incremental as it builds on existing counterfactual explanation methods.
The paper tackles the problem of finding coherent counterfactual explanations for complex data with mixed continuous and discrete variables by proposing a novel 'mixed polytope' constraint set and efficient search algorithms based on mixed integer programming, which avoids brute-force enumeration and also generates diverse explanations.
This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming. We are concerned with complex data in which variables may take any value from a contiguous range or an additional set of discrete states. We propose a novel set of constraints that we refer to as a "mixed polytope" and show how this can be used with an integer programming solver to efficiently find coherent counterfactual explanations i.e. solutions that are guaranteed to map back onto the underlying data structure, while avoiding the need for brute-force enumeration. We also look at the problem of diverse explanations and show how these can be generated within our framework.