Web: http://arxiv.org/abs/2206.07387

June 16, 2022, 1:10 a.m. | Sebastian Bordt, Uddeshya Upadhyay, Zeynep Akata, Ulrike von Luxburg

cs.LG updates on arXiv.org arxiv.org

When do gradient-based explanation algorithms provide meaningful
explanations? We propose a necessary criterion: their feature attributions need
to be aligned with the tangent space of the data manifold. To provide evidence
for this hypothesis, we introduce a framework based on variational autoencoders
that allows to estimate and generate image manifolds. Through experiments
across a range of different datasets -- MNIST, EMNIST, CIFAR10, X-ray pneumonia
and Diabetic Retinopathy detection -- we demonstrate that the more a feature
attribution is aligned with …

arxiv gradient hypothesis lg manifold

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY