dilyabareeva / quanda

A toolkit for quantitative evaluation of data attribution methods.
https://quanda.readthedocs.io
MIT License
33 stars 0 forks source link

Data Attribution Strict Assumptions #118

Closed dilyabareeva closed 1 day ago

dilyabareeva commented 3 months ago

As far as I understand, in an ideal world if we apply data attribution methods to a model, the model is 1) supposed to be trained from scratch (not pre-trained on a larger dataset); 2) not supposed to involve data augmentation. But how are we supposed to train any (non-MNIST) models like that so that they don't perform bad?