Formal Logic Inference Guided Uncertainty Quantification for Personalized Federated Learning
Journal of Artificial Intelligence Research · 08.07.2026 · 86
DOI: 10.1613/jair.1.21429 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Artificial Intelligence Research, online erschienen am 08.07.2026. Verfasst von Guocheng He und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Federated Learning (FL) enables privacy-preserving model training across heterogeneous distributed systems, such as smartgrid forecasting or traffic-flow prediction from geographically dispersed sensors and devices. A key challenge in such settings is capturing client-specific patterns while addressing data heterogeneity and uncertainty at scale. Existing approaches, including Bayesian Neural Networks (BNNs) and clustering-based methods, struggle with scalability and consistent personalization. We propose LogiCP, a novel FL framework that integrates formal logic reasoning with uncertainty quantification (UQ) to support scalable and personalized learning with theoretical guarantees. LogiCP uses Signal Temporal Logic (STL) to extract temporal patterns and form semantically coherent client clusters, controlling intra-cluster heterogeneity. Within each cluster, LogiCP applies decentralized Conformal Prediction (CP) to produce distribution-free prediction intervals with mathematical guarantees that encompass the real value. LogiCP dynamically assigns clients to clusters at runtime without retraining, improving practicality. Evaluations on three real-world datasets—traffic, temperature, and electricity—show that LogiCP consistently outperforms BNN-, clustering-, and CP-based baselines, achieving up to a 95% improvement in client-level MSE while maintaining strong scalability.
Zitieren
APA
He, G., An, Z., & Ma, M. (2026). Formal Logic Inference Guided Uncertainty Quantification for Personalized Federated Learning. Journal of Artificial Intelligence Research, 86. https://doi.org/10.1613/jair.1.21429
Vancouver
He G, An Z, Ma M. Formal Logic Inference Guided Uncertainty Quantification for Personalized Federated Learning. Journal of Artificial Intelligence Research. 2026;86. doi:10.1613/jair.1.21429
BibTeX
@article{He2026,
author = {He, Guocheng and An, Ziyan and Ma, Meiyi},
title = {Formal Logic Inference Guided Uncertainty Quantification for Personalized Federated Learning},
journal = {Journal of Artificial Intelligence Research},
year = {2026},
volume = {86},
doi = {10.1613/jair.1.21429}
}
EUVIMED