Diffeomorphic Counterfactuals with Generative Models
This work addresses the need for better explainability in AI systems, particularly for users requiring transparent decision-making processes, though it appears incremental as it builds on existing generative model techniques.
The paper tackles the problem of generating human-interpretable counterfactual explanations for neural network classification decisions by proposing a method that uses diffeomorphic coordinate transformations and gradient ascent, validated through theoretical analysis and empirical measures.
Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic coordinate transformation and then perform gradient ascent in these coordinates to find counterfactuals which are classified with great confidence as a specified target class. We propose two methods to leverage generative models to construct such suitable coordinate systems that are either exactly or approximately diffeomorphic. We analyze the generation process theoretically using Riemannian differential geometry and validate the quality of the generated counterfactuals using various qualitative and quantitative measures.