AI RESEARCH
Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC
arXiv CS.LG
•
ArXi:2606.04857v1 Announce Type: new Standard IMVC evaluation retrains separate models for different missing-data configurations. We show that this paradigm obscures a fundamental vulnerability: missing rate alone is insufficient to characterize data incompleteness. Specifically, we show that protocols with identical nominal missing rates can differ by up to $50\times$ in their proportion of fully observed samples, inducing drastically different learning regimes.