Can I read EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejection on EtoBox?

EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejection by Qu, Yunni; Wellnitz, James; Tropsha, Alexander; Oliva, Junier is a scholarly article available to read on EtoBox.

What is EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejection about?

Expansive Matching of Experts (EMOE) is a novel method that utilizes support-expanding, extrapolatory pseudo-labeling to improve prediction and uncertainty based rejection on out-of-distribution (OOD) points. We propose an expansive data augmentation technique that generates OOD instances in a latent space, and an empirical trial based approach to filter out augmented expansive points for pseudo-labeling. EMOE utilizes a diverse set of multiple base experts as pseudo-labelers on the augmented data to improve OOD performance through a shared MLP with multiple heads (one per expert). We demonstrate that EMOE achieves superior performance compared to state-of-the-art methods on tabular data.

Author

Qu, Yunni; Wellnitz, James; Tropsha, Alexander; Oliva, Junier

Published

2024

Language

EN