2 papers
stat.ML2026
Informative Label Missingness in Multiclass Classification Information Geometry and Excess Risk
Fariborz Setoudehtazang, Geoffrey J. McLachlan
Informative label missingness can change the usual efficiency ordering between completely and partially labelled classifiers because the pattern of missing labels may itself carry…
stat.CO2026
Favourable Missingness in Semi-Supervised Classification for Exponential Mixture Models
Huanchao Zhou, Jinran Wu, Fariborz Setoudehtazang +1
Semi-supervised classifiers are commonly trained from samples in which all features are observed but some class labels are missing. When label missingness is independent of the obs…