How robust are unsupervised representation learning methods (e.g. SSL) to distirbution shift compared to supervised learning?
𝐒𝐡𝐨𝐫𝐭 𝐚𝐧𝐬𝐰𝐞𝐫: Quite!
𝐋𝐨𝐧𝐠 𝐚𝐧𝐬𝐰𝐞𝐫: Our #ICLR2023 paper http://arxiv.org/pdf/2206.08871.pdf
Joint work with Imant Daunhawer & Amartya Sanyal @amartya
One more thing: Compared to supervised learning, unsupervised learning methods consistently suffers from less performance drop going from in-distribution to out-of-distribution evaluation! More generalisation wins for not using labels. (6/n)