Federated Learning Frameworks for Collaborative Model Training in Privacy-Conscious Distributed Systems
Keywords:
Federated Learning, Distributed Training, Privacy-Preserving AI, Decentralized Systems, Collaborative Learning, Edge Computing, Data SovereigntyAbstract
Federated Learning (FL) offers a decentralized approach to training machine learning models collaboratively across multiple devices or institutions while preserving data privacy. With increasing concerns around data ownership, regulatory compliance, and distributed computation, FL has emerged as a pivotal framework in privacy-conscious model training. This paper explores foundational federated learning frameworks available, analyzes their architectural design, privacy mechanisms, and performance trade-offs, and highlights unresolved challenges. We also discuss future opportunities and visualize common FL pipelines and models, concluding with a review of existing literature to identify research gaps.
References
McMahan, H. Brendan, et al. "Communication-Efficient Learning of Deep Networks from Decentralized Data." AISTATS, 2017.
Bonawitz, K., et al. "Practical Secure Aggregation for Privacy-Preserving Machine Learning." ACM CCS, 2017.
Konecny, Jakub, et al. "Federated Optimization: Distributed Machine Learning for On-Device Intelligence." arXiv preprint, 2016.
Smith, Virginia, et al. "Federated Multi-Task Learning." NeurIPS, 2017.
Shokri, Reza, and Vitaly Shmatikov. "Privacy-Preserving Deep Learning." ACM CCS, 2015.
Li, Tian, et al. "Federated Optimization in Heterogeneous Networks." MLSys, 2019.
Google AI Blog. "Federated Learning: Collaborative Machine Learning without Centralized Training Data." 2017.
OpenMined. "PySyft: Enabling Privacy-Preserving Machine Learning." 2018.
Reddi, Sashank J., et al. "Adaptive Federated Optimization." ICLR, 2020.
Zhao, Yue, et al. "Federated Learning with Non-IID Data." arXiv preprint, 2018.
Li, Qinbin, et al. "Privacy-Preserving Federated Brain Tumour Segmentation." MICCAI, 2019.
Bagdasaryan, Eugene, et al. "How to Backdoor Federated Learning." AISTATS, 2020.
Charles, Zachary, et al. "On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima." arXiv, 2018.
Caldas, Sebastian, et al. "LEAF: A Benchmark for Federated Settings." arXiv, 2019.
He, Chaoyang, et al. "FedML: A Research Library and Benchmark for Federated Machine Learning." arXiv preprint, 2020.
