# Semi-Decentralized Federated Edge Learning with Data and Device Heterogeneity arXiv: https://arxiv.org/abs/2112.10313 ยท HTML: https://mlsanity.com/paper/2112.10313/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 25 of its 44 references that are in the map. - First posted on arXiv 20 Dec 2021. ## Builds on (most cited first, 25 of 25) - [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016) - [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016) - [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020) - [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017) - [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018) - [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019) - [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019) - [Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge](https://mlsanity.com/paper/1804.08333/) (2018) - [The Non-IID Data Quagmire of Decentralized Machine Learning](https://mlsanity.com/paper/1910.00189/) (2019) - [FedML: A Research Library and Benchmark for Federated Machine Learning](https://mlsanity.com/paper/2007.13518/) (2020) - [Asynchronous Federated Optimization](https://mlsanity.com/paper/1903.03934/) (2019) - [Client-Edge-Cloud Hierarchical Federated Learning](https://mlsanity.com/paper/1905.06641/) (2019) - [Federated Learning over Wireless Fading Channels](https://mlsanity.com/paper/1907.09769/) (2019) - [The Roadmap to 6G -- AI Empowered Wireless Networks](https://mlsanity.com/paper/1904.11686/) (2019) - [D2: Decentralized Training over Decentralized Data](https://mlsanity.com/paper/1803.07068/) (2018) - [Communication-Efficient Edge AI: Algorithms and Systems](https://mlsanity.com/paper/2002.09668/) (2020) - [Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning](https://mlsanity.com/paper/2007.07174/) (2020) - [SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead](https://mlsanity.com/paper/1910.01355/) (2019) - [Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD](https://mlsanity.com/paper/1810.08313/) (2018) - [Decentralized Federated Learning: Balancing Communication and Computing Costs](https://mlsanity.com/paper/2107.12048/) (2021) - [6G Internet of Things: A Comprehensive Survey](https://mlsanity.com/paper/2108.04973/) (2021) - [Quantized Federated Learning under Transmission Delay and Outage Constraints](https://mlsanity.com/paper/2106.09397/) (2021) - [Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Data](https://mlsanity.com/paper/2104.12678/) (2021) - [Multi-Level Local SGD for Heterogeneous Hierarchical Networks](https://mlsanity.com/paper/2007.13819/) (2020) - [Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients](https://mlsanity.com/paper/2112.04737/) (2021) ## Built on by (most cited first, 12 of 12) - [A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency](https://mlsanity.com/paper/2307.10655/) (2023) - [Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networking](https://mlsanity.com/paper/2205.13054/) (2022) - [Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning](https://mlsanity.com/paper/2305.16854/) (2023) - [Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients](https://mlsanity.com/paper/2402.11198/) (2024) - [An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarios](https://mlsanity.com/paper/2402.01723/) (2024) - [Communication-Efficient Federated Optimization over Semi-Decentralized Networks](https://mlsanity.com/paper/2311.18787/) (2023) - [Heterogeneity-Aware Cooperative Federated Edge Learning with Adaptive Computation and Communication Compression](https://mlsanity.com/paper/2409.04022/) (2024) - [A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learning](https://mlsanity.com/paper/2410.07881/) (2024) - [Resource-Constrained Decentralized Federated Learning via Personalized Event-Triggering](https://mlsanity.com/paper/2211.12640/) (2022) - [Trust-free Personalized Decentralized Learning](https://mlsanity.com/paper/2410.11378/) (2024) - [TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning](https://mlsanity.com/paper/2412.11448/) (2024) - [Towards a Distributed Federated Learning Aggregation Placement using Particle Swarm Intelligence](https://mlsanity.com/paper/2504.16227/) (2025) ## Abstract (arXiv) Federated edge learning (FEEL) has attracted much attention as a privacy-preserving paradigm to effectively incorporate the distributed data at the network edge for training deep learning models. Nevertheless, the limited coverage of a single edge server results in an insufficient number of participated client nodes, which may impair the learning performance. In this paper, we investigate a novel framework of FEEL, namely semi-decentralized federated edge learning (SD-FEEL), where multiple edge servers are employed to collectively coordinate a large number of client nodes. By exploiting the low-latency communication among edge servers for efficient model sharing, SD-FEEL can incorporate more training data, while enjoying much lower latency compared with conventional federated learning. We detail the training algorithm for SD-FEEL with three main steps, including local model update, intra-cluster, and inter-cluster model aggregations. The convergence of this algorithm is proved on non-independent and identically distributed (non-IID) data, which also helps to reveal the effects of key parameters on the training efficiency and provides practical design guidelines. Meanwhile, the heterogeneity of edge devices may cause the straggler effect and deteriorate the convergence speed of SD-FEEL. To resolve this issue, we propose an asynchronous training algorithm with a staleness-aware aggregation scheme for SD-FEEL, of which, the convergence performance is also analyzed. The simulation results demonstrate the effectiveness and efficiency of the proposed algorithms for SD-FEEL and corroborate our analysis.