Stochastic Mirror-Prox Optimisation of Group Distributionally Robust Multimodal Logistic Regression for Multilingual Fact-Checking Verdict Prediction
Mathematics · 02.10.2026 · 14 (19) · 3574
DOI: 10.3390/math14193574 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 02.10.2026. Verfasst von Shuyun Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper asks whether group distributionally robust optimisation raises the worst-group macro-F1 of a block-masked multimodal logistic regression with availability indicators for multilingual fact-checking. Stochastic Mirror-Prox solves the resulting convex–concave saddle-point problem. The corpus pools 49,584 X-Fact and MediaEval records with 90 language labels. On the in-domain split, the robust solution lifts worst-group macro-F1 from 0.313 under pooled empirical risk minimisation to 0.401 (95% interval of the gain [0.025,0.134]). Overall macro-F1 drops by 0.040, and dispersion of balanced accuracy across languages falls from 0.166 to 0.131. The gain lies in X-Fact claim groups and the cost in MediaEval posts (macro-F1 0.887 to 0.809). Removing the availability indicators moves no worst-group or overall macro-F1 by more than 0.007. The worst-group difference is negative on unseen languages and not resolved on unseen sites or events. A Friedman test detects no difference between solvers in typical group performance. At equal numbers of sampled records, stochastic mirror descent reaches a smaller mean duality gap than Mirror-Prox at each measured mini-batch size from 2 to 128. On this instance, extrapolation does not repay its second call.
Zitieren
APA
Li, S., Si, F., Mo, D., & He, C. (2026). Stochastic Mirror-Prox Optimisation of Group Distributionally Robust Multimodal Logistic Regression for Multilingual Fact-Checking Verdict Prediction. Mathematics, 14(19), 3574. https://doi.org/10.3390/math14193574
Vancouver
Li S, Si F, Mo D, He C. Stochastic Mirror-Prox Optimisation of Group Distributionally Robust Multimodal Logistic Regression for Multilingual Fact-Checking Verdict Prediction. Mathematics. 2026;14(19):3574. doi:10.3390/math14193574
BibTeX
@article{Li2026,
author = {Li, Shuyun and Si, Fan and Mo, Dongxu and He, Chao},
title = {Stochastic Mirror-Prox Optimisation of Group Distributionally Robust Multimodal Logistic Regression for Multilingual Fact-Checking Verdict Prediction},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {19},
pages = {3574},
doi = {10.3390/math14193574}
}
EUVIMED