Diffeomorphic Counterfactuals With Generative Models

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 46; no. 5; pp. 3257 - 3274
Main Authors: Dombrowski, Ann-Kathrin, Gerken, Jan E., Muller, Klaus-Robert, Kessel, Pan
Format: Journal Article
Language:English
Published: United States IEEE 01.05.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Annan data- och informationsvetenskap
Artificial intelligence
Computational modeling
Computer graphics and computer vision
Coordinate transformations
Counterfactual Explanations
Data Manifold
Data models
Datorgrafik och datorseende
Differential geometry
Explainable Artificial Intelligence
Generative Models
Geometri
Geometry
Manifolds
Neural networks
Other Computer and Information Science
Semantics
Task analysis
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2023.3339980