Diffeomorphic Counterfactuals with Generative Models
Artikel i vetenskaplig tidskrift, 2023
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.
Data Manifold
Geometry
Task analysis
Generative Models
Semantics
Data models
Manifolds
Counterfactual Explanations
Explainable Artificial Intelligence
Computational modeling
Artificial intelligence
Författare
Ann Kathrin Dombrowski
Technische Universität Berlin
Jan Gerken
Chalmers, Matematiska vetenskaper, Algebra och geometri
Klaus Robert Muller
Technische Universität Berlin
Pan Kessel
Genentech
IEEE Transactions on Pattern Analysis and Machine Intelligence
0162-8828 (ISSN) 19393539 (eISSN)
Vol. In PressÄmneskategorier (SSIF 2011)
Datavetenskap (datalogi)
DOI
10.1109/TPAMI.2023.3339980
PubMed
38055368