Hierarchical Federated Learning ACROSS Heterogeneous Cellular Networks

By Mehdi Salehi Heydar Abad, Emre Ozfatura, Deniz Gündüz, Özgür Erçetin. 2019

388 citations recorded by the source corpus.

We consider federated edge learning (FEEL), where mobile users (MUs) collaboratively learn a global model by sharing local updates on the model parameters rather than their datasets, with the help of a mobile base station (MBS). We optimize the resource allocation among MUs to reduce the communication latency in learning iterations. Observing that the performance in this centralized setting is limited due to the distance of the cell-edge users to the MBS, we introduce small cell base stations (SBSs) orchestrating FEEL among MUs within their cells, and periodically exchanging model updates with the MBS for global consensus. We show that this hierarchical federated learning (HFL) scheme significantly reduces the communication latency without sacrificing the accuracy.

Subfields: Artificial Intelligence, Computer Networks and Communications, Electrical and Electronic Engineering

How researchers see this paper

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

In Artificial Intelligence

In Computer Networks and Communications

In Electrical and Electronic Engineering

Citations in the corpus

FedML: A Research Library and Benchmark for Federated Machine Learning (2020, background): “As demonstrated in Figure 3, FL has various topology deﬁnitions, such as vertical FL [34, 35, 36, 37, 38, 39, 40], split learning [41, 42], decentralized FL [43, 44, 45, 46], and Hierarchical FL [47, 48, 49, 50, 51, 52].”
Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “In [44], the authors discuss a communication-efficient hierarchical federated learning approach in which mobile users”
Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications (2020, methodology): “In addition to client scheduling and resource management, to remedy this type of straggler problem, it is useful to utilize advanced multiple access control techniques, such as proactive scheduling via channel prediction and multihop relaying [71], [133], [134].”
Communication-Efficient Edge AI: Algorithms and Systems (2020, methodology): “[205] proposed a hierarchical federated learning scheme by introducing small”
One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysis (2020, background): “In [20], a hierarchical FEEL framework is introduced in a cellular network.”
A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, background): “Abad et al. [133] proposed an approach targeting a heterogeneous cellular network.”
On Analog Gradient Descent Learning Over Multiple Access Fading Channels (2019, background): “Other recent studies considered federated learning with heterogeneous [18], [19] or redundant [20] data, including overthe-air aggregation techniques via MAC with known channel states [19], [20], digital gradient transmissions [21], and privacy over MAC [22].”
Distributed Learning in Wireless Networks: Recent Progress and Future Challenges (2021, background): “In [12], hierarchical FL is proposed, where devices are grouped into clusters, and devices within each cluster carry out local learning with the help of a small BS or a cluster head, while a global model is trained at the macro BS.”
Federated Learning in Smart City Sensing: Challenges and Opportunities (2020, neutral): “Since the data does not transfer, it does not reveal user privacy or affect data speciﬁcations [124].”
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2019, background): “Structured update means restricting the model updates to have a pre-specified structure, specifically, 1) low-rank matrix; or 2) sparse matrix [202], [203].”