search

facebookresearch / DomainBed

DomainBed is a suite to test domain generalization algorithms
MIT License
1.42k stars 299 forks source link

Predefined groups for training groupDRO #39

Closed pavanteja295 closed 3 years ago

pavanteja295 commented 3 years ago

Hello, Thank you very much for this amazing comparison. I have slight confusion regarding the implementation of groupDRO. In the groupDRO paper authors carefully generate the training datasets to contain a mixture of groups that are defined by leveraging human knowledge (identify some spurious correlations).

However, in this repository and comparison in the paper I fail to see such a construction of predefined groups for groupDRO. As far as I understand the implementation, dataset is randomly sampled and each sample in the minibatch is considered to arrive from one particular training group. I understand that predefining groups on a new dataset is difficult but is it justifiable to compare groupDRO with such a relaxation. I tried to look into the paper associated with this repo, however, I did not see any mention on the same.

Thank you so much for your time and patience!

lopezpaz commented 3 years ago

This repository deals with domain generalization problems. That is, algorithms receive minibatches = ((X1, Y1), ..., (XG, YG)), where (Xg, Yg) is a minibatch of labeled examples from domain (group) g, for all g = 1, ..., G.