<ul><li>ADA (Anchor Data Augmentation) is evaluated and compared to prior approaches on tasks involving out-of-distribution robustness.</li><li>Four out-of-distribution datasets are used, including RCFashionMNIST, Communities and Crime, SkillCraft1 Master Table, and Drug-target Interactions.</li><li>Results show that ADA is competitive with C-Mixup and other data augmentation strategies, and significantly outperforms them on the SkillCraft dataset.</li><li>ADA reduces the error by around 15% compared to the ERM solution on the SkillCraft data.</li></ul>

ADA's Impact on Out-of-Distribution Robustness

Discover more