Secure and Scalable AI: Insights into Federated Learning Algorithms and Platforms
M. Aishwarya, J. Umesh Chandra, M. Farhan Ali, M. Bharathi, T. Aditya Sai Srinivas · Journal of Communication Engineering and VLSI Design · 2024
This paper takes a closer look at the rapidly advancing field of Federated Learning (FL), a decentralized machine learning approach that focuses on preserving data privacy by training models across multiple devices. It highlights key algorithms like Federated Averaging (FedAvg) and its more refined versions Hierarchical Federated Averaging (HierFAVG) and Federated Matched Averaging (FedMA) which improve model aggregation techniques. The discussion extends to both Horizontal and Vertical Federated Learning (HFL and VFL), illustrating how they handle data partitioning and communication differently. Additionally, the paper reviews prominent FL frameworks and simulators, including TensorFlow Federated (TFF), PySyft, Flower, and FedML, emphasizing their roles in facilitating experiments and ensuring scalability. Critical features like data distribution, communication topologies, and security measures in FL simulators are explored. Ultimately, the paper offers a comprehensive overview of FL frameworks, algorithms, and architectures, showcasing their ability to advance distributed AI while tackling the challenges of data diversity and privacy.