The 45th Seminar
Date and Time: Dec. 13th 5:00 pm – 6:00 pm(JST)
Venue: Zoom webinar
Speaker: Teresa Yeo (EPFL)
Title: Robustness via Cross Domain Ensembles
Neural networks are able to learn complex functions on in-distribution data. However, their predictions are unreliable under distribution shifts, i.e. they are not robust. In this talk, I will present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues and ensembling them into one strong prediction. The merging is done in a straightforward but principled manner based on the uncertainty associated with each prediction. Evaluations performed on multiple tasks and datasets under a wide range of shifts demonstrate that the proposed method is more robust than the baselines.