EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FedQuAD: Fast-Converging Curvature-Aware Federated Learning for Credit Default Prediction from Private Accounting Data

Dingwen Bai, MuGa WaEr, Qichun Wu

Mathematics · 17.03.2026 · 14 (6) · 1012

DOI: 10.3390/math14061012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 17.03.2026. Verfasst von Dingwen Bai und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Credit default prediction from firm-level accounting statements is central to risk management, yet the underlying financial data are highly sensitive and often siloed across banks, auditors, and platforms. Federated learning (FL) offers a practical route to collaborative modeling without centralizing raw records, but standard FL optimization can converge slowly under severe client heterogeneity, heavy-tailed accounting features, and label imbalance typical of default events. This paper proposes FedQuAD, a novel fast-converging FL algorithm that couples (i) quasi-Newton curvature aggregation on the server with a lightweight limited-memory update to accelerate global progress, (ii) a proximal variance-reduced local solver that stabilizes client drift under non-IID accounting distributions, and (iii) federated robust standardization of tabular financial ratios via secure aggregated quantile statistics to mitigate scale instability and outliers. FedQuAD is communication-efficient by design: It transmits compact gradient and curvature sketches and adapts local computation to each client’s stochasticity and drift. We provide convergence guarantees for strongly convex default-risk objectives (logistic and calibrated GLM losses) under bounded heterogeneity, and extend the analysis to nonconvex deep tabular models via expected stationarity bounds. Experiments on public credit-risk benchmarks with simulated cross-silo (institutional) partitions demonstrate that FedQuAD reaches target AUC and calibration error with substantially fewer communication rounds than representative baselines while maintaining privacy constraints compatible with secure aggregation and optional client-level differential privacy accounting.

Zitieren

APA

Bai, D., WaEr, M., & Wu, Q. (2026). FedQuAD: Fast-Converging Curvature-Aware Federated Learning for Credit Default Prediction from Private Accounting Data. Mathematics, 14(6), 1012. https://doi.org/10.3390/math14061012

Vancouver

Bai D, WaEr M, Wu Q. FedQuAD: Fast-Converging Curvature-Aware Federated Learning for Credit Default Prediction from Private Accounting Data. Mathematics. 2026;14(6):1012. doi:10.3390/math14061012

BibTeX
@article{Bai2026,
  author = {Bai, Dingwen and WaEr, MuGa and Wu, Qichun},
  title = {FedQuAD: Fast-Converging Curvature-Aware Federated Learning for Credit Default Prediction from Private Accounting Data},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {6},
  pages = {1012},
  doi = {10.3390/math14061012}
}
Kostenlos starten →