works on
incompleteness divergence 1missing data robustness 1multi-view learning 1train-once learning 1transformer architecture 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC

Haolu Liu, Xiyue Wang, Xuanting Xie +2

The paper identifies that identical missing-data rates can hide large differences in the amount of fully observed samples, causing a vulnerability they call incompleteness divergen…