تقرير
FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
العنوان: | FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler |
---|---|
المؤلفون: | Peng, Hongyi, Yu, Han, Tang, Xiaoli, Li, Xiaoxiao |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Distributed, Parallel, and Cluster Computing |
الوصف: | Federated learning (FL) enables collaborative machine learning across distributed data owners, but data heterogeneity poses a challenge for model calibration. While prior work focused on improving accuracy for non-iid data, calibration remains under-explored. This study reveals existing FL aggregation approaches lead to sub-optimal calibration, and theoretical analysis shows despite constraining variance in clients' label distributions, global calibration error is still asymptotically lower bounded. To address this, we propose a novel Federated Calibration (FedCal) approach, emphasizing both local and global calibration. It leverages client-specific scalers for local calibration to effectively correct output misalignment without sacrificing prediction accuracy. These scalers are then aggregated via weight averaging to generate a global scaler, minimizing the global calibration error. Extensive experiments demonstrate FedCal significantly outperforms the best-performing baseline, reducing global calibration error by 47.66% on average. Comment: This paper has been accepted by ICML'24 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2405.15458 |
رقم الأكسشن: | edsarx.2405.15458 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |