Frustratingly Easy Environment Discovery for Invariant Learning

Standard training via empirical risk minimization may result in making predictions that overly rely on spurious correlations. This can degrade the generalization to out-of-distribution settings where these correlations no longer hold. Invariant learning has been shown to be a promising approach for...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Samira Zare, Hien Van Nguyen
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	MDPI AG 2024-01-01
Цуврал:	Computer Sciences & Mathematics Forum
Нөхцлүүд:	environment discovery invariant learning out-of-distribution generalization biased data
Онлайн хандалт:	https://www.mdpi.com/2813-0324/9/1/2
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!