Do Explanations Explain? Model Knows Best
Khakzar A, Khorsandi P, Nobahari R, Navab N (2022)
Publication Type: Conference contribution
Publication year: 2022
Journal
Publisher: IEEE Computer Society
Book Volume: 2022-June
Pages Range: 10234-10243
Conference Proceedings Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Event location: New Orleans, LA, USA
ISBN: 9781665469463
DOI: 10.1109/CVPR52688.2022.01000
Abstract
It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations (attributions) point to different features as being important. The phenomenon raises the question, which explanation to trust? We propose a framework for evaluating the explanations using the neural network model itself. The framework leverages the network to generate input features that impose a particular behavior on the output. Using the generated features, we devise controlled experimental setups to evaluate whether an explanation method conforms to an axiom. Thus we propose an empirical framework for axiomatic evaluation of explanation methods. We evaluate well-known and promising explanation solutions using the proposed framework. The framework provides a toolset to reveal properties and drawbacks within existing and future explanation solutions.11https://github.com/CAMP-eXplain-AI/Do-Explanations-Explain
Involved external institutions
Technische Universität München (TUM)
Germany (DE)
Quebec AI Institute / Quebec Artificial Intelligence Institute / Montreal Institute for Learning Algorithms (MILA)
Canada (CA)
Germany (DE)
Quebec AI Institute / Quebec Artificial Intelligence Institute / Montreal Institute for Learning Algorithms (MILA)
Canada (CA)
How to cite
APA:
Khakzar, A., Khorsandi, P., Nobahari, R., & Navab, N. (2022). Do Explanations Explain? Model Knows Best. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 10234-10243). New Orleans, LA, USA: IEEE Computer Society.
MLA:
Khakzar, Ashkan, et al. "Do Explanations Explain? Model Knows Best." Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA IEEE Computer Society, 2022. 10234-10243.
BibTeX: Download