aiqbench analysis
This research introduces GrAUC-PFL, a federated learning framework that directly optimizes the Area Under the Curve (AUC) metric while preserving patient data privacy across geographically distributed healthcare institutions. By employing graph-based regularization, the method ensures model similarity between neighboring entities with comparable data distributions, addressing the challenge of institutional heterogeneity without centralizing sensitive information. The approach demonstrates enhanced discriminative performance for diagnostic and risk-prediction models in scenarios where local data sharing is restricted by governance policies.
Geographically Regularized AUC-Maximizing Personalized Federated Learning
arXiv:2609.08379v1 Announce Type: new Abstract: Accurate diagnostic and risk-prediction models are important for supporting clinical decision-making during infectious disease outbreaks. However, privacy and governance requirements may restrict patient-level data sharing across healthcare institutions, and data distributions often vary. Moreover, AUC is widely used to evaluate discriminative performance, motivating its direct optimization in model development. We propose geographically regularized AUC-maximizing personalized federated learning (GrAUC-PFL), which directly optimizes a smooth pairwise AUC surrogate to learn personalized models while keeping patient-level data local and accounting for institutional heterogeneity. Graph-based regularization encourages geographically neighboring institutions to have similar coefficient vectors while retaining a personalized models. Simulations and a real-data application suggest improved discriminative performance, particularly when geographically neighboring institutions have similar data-generating characteristics.
Abstract:Accurate diagnostic and risk-prediction models are important for supporting clinical decision-making during infectious disease outbreaks. However, privacy and governance requirements may restrict patient-level data sharing across healthcare institutions, and data distributions often vary. Moreover, AUC is widely used to evaluate discriminative performance, motivating its direct optimization in model development. We propose geographically regularized AUC-maximizing personalized federated learning (GrAUC-PFL), which directly optimizes a smooth pairwise AUC surrogate to learn personalized models while keeping patient-level data local and accounting for institutional heterogeneity. Graph-based regularization encourages geographically neighboring institutions to have similar coefficient vectors while retaining a personalized models. Simulations and a real-data application suggest improved discriminative performance, particularly when geographically neighboring institutions have similar data-generating characteristics.
Machine Learning (cs.LG); Methodology (stat.ME)
arXiv:2609.08379 [cs.LG]
(or arXiv:2609.08379v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.08379 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 210 words
Related coverage
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · Sep 24, 2026
For Love of the Lightcone, Don't Partisanize AI Safety
LessWrong · Sep 17, 2026
FedLoRD: Personalized Federated Learning based on Low-Rank Structures of Model Parameter Differences
arXiv · Oct 14, 2026
Why I Left Google DeepMind
LessWrong · Jul 15, 2026