most citedRepresentation via Representations: Domain Generalization via Adversarially Learned Invariant Representations

11 citations · 15 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2021★ 4 cited

Grounding Representation Similarity with Statistical Testing

Frances Ding, Jean-Stanislas Denain, Jacob Steinhardt

To understand neural network behavior, recent works quantitatively compare different networks' learned representations using canonical correlation analysis (CCA), centered kernel a…

cs.LG2020★ 11 cited

Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations

Zhun Deng, Frances Ding, Cynthia Dwork +4

We investigate the power of censoring techniques, first developed for learning {\em fair representations}, to address domain generalization. We examine {\em adversarial} censoring…