Edge-Assisted Hierarchical Federated Learning with Non-IID Data

By Lumin Liu, Jun Zhang, Shenghui Song, Khaled Ben Letaief. 2019

68 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning (2020, methodology): “Another line of work has focused on approaches based on decentralized learning [33], [34] or edge-assisted hierarchical physical layer topologies [35].”
Federated Learning: Challenges, Methods, and Future Directions (2019, background): “Finally, hierarchical communication patterns have also been proposed [68, 70] to further ease the burden on the central server, by first leveraging edge servers to aggregate the updates from edge devices and then relying on a cloud server to aggregate updates from edge servers.”
Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective (2020, background): “Hierarchical FL networks [20] have also been proposed where multiple edge servers perform partial model aggregation first, whose outputs are further aggregated by a cloud server.”
Communication-Efficient Federated Learning for Wireless Edge Intelligence in IoT (2020, unknown): “[17] proposed having clients aggregate with intermediate servers which then aggregate with a main server with two given frequencies.”
TiFL: A Tier-based Federated Learning System (2020, methodology): “For Cifar10, we shard the dataset unevenly in a similar way and limit the number of classes to 5 per client (non-IID(5)) following [41], [24] unless explicitly mentioned otherwise.”
Mobile Edge Intelligence and Computing for the Internet of Vehicles (2019, background): “As shown in a recent study [128], such edge-assisted hierarchical federated learning reaches a desired model performance with much less communication.”
Machine Learning at the Network Edge: A Survey (2019, background): “[87] Intermediate edge aggregation to reduce communication cost during federated learning Wang et al.”
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, background): “Many other studies also design specialize approach for non-IID data [221, 111, 118, 210].”
A Survey on Federated Learning for Resource-Constrained IoT Devices (2021, unknown): “For instance, Liu et al. [146] considered an intermediate model aggregator for reducing instances during device-cloud communication.”
Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “, more passes over dataset before communication [23], [98] (b) Two-stream training with global model as a reference [99] and (c) Intermediate edge server aggregation [100].”
Enhancing Privacy via Hierarchical Federated Learning (2020, background): “A restricted version of HFL, considering only three layers, has been presented in [13]–[15].”
A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, background): “[55] highlighted the enormous number of communication rounds needed in FL to improve the model accuracy, which results in unendurable latency and network saturation.”