Tweeted By @DeepMind
Is it possible to transform sensitive user data in a way that π¨πΆπ’π³π’π―π΅π¦π¦π΄ fairness while still being useful for (unknown) downstream applications?
β DeepMind (@DeepMind) October 25, 2022
Β
Introducing LASSI: a new provably fair representation learning method for high-dimensional data: https://t.co/ww1I6qd4jA pic.twitter.com/D4VpJLY1qL