Do Concept Bottleneck Models Learn as Intended?
ICLR-21 Workshop on Responsible AI
MetadataShow full item record
Margeloiu, A., Ashman, M., Bhatt, U., Chen, Y., Jamnik, M., & Weller, A. (2021). Do Concept Bottleneck Models Learn as Intended?. CoRR https://doi.org/10.17863/CAM.80941
Concept bottleneck models map from raw inputs to concepts, and then from concepts to targets. Such models aim to incorporate pre-specified, high-level concepts into the learning procedure, and have been motivated to meet three desiderata: interpretability, predictability, and intervenability. However, we find that concept bottleneck models struggle to meet these goals. Using post hoc interpretability methods, we demonstrate that concepts do not correspond to anything semantically meaningful in input space, thus calling into question the usefulness of concept bottleneck models in their current form.
cs.LG, cs.LG, cs.AI
This record's DOI: https://doi.org/10.17863/CAM.80941
This record's URL: https://www.repository.cam.ac.uk/handle/1810/333521
All Rights Reserved
Licence URL: http://www.rioxx.net/licenses/all-rights-reserved