mlsanityData to 14 Oct 2026

A Generalized Hierarchical Federated Learning Framework with Theoretical Guarantees

arXiv 2505.08145 ↗First posted 13 May 2025cs.LG cs.DC cs.ITcited by 2

Not on the map. Why?

Abstract (arXiv)

Almost all existing hierarchical federated learning (FL) models are limited to two aggregation layers, restricting scalability and flexibility in complex, large-scale networks. In this work, we propose a Multi-Layer Hierarchical Federated Learning framework (QMLHFL), which appears to be the first study that generalizes hierarchical FL to arbitrary numbers of layers and network architectures through nested aggregation, while employing a layer-specific quantization scheme to meet communication constraints. We develop a comprehensive convergence analysis for QMLHFL and derive a general convergence condition and rate that reveal the effects of key factors, including quantization parameters, hierarchical architecture, and intra-layer iteration counts. Furthermore, we determine the optimal number of intra-layer iterations to maximize the convergence rate while meeting a deadline constraint that accounts for both communication and computation times. Our results show that QMLHFL consistently achieves high learning accuracy, even under high data heterogeneity, and delivers notably improved performance when optimized, compared to using randomly selected values.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 45 references that are in the map. First posted on arXiv 13 May 2025.

Builds on

20 of 45 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  4. 2020HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learningcited by 74
  5. 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 51
  6. 2021Hierarchical Federated Learning with Quantization: Convergence Analysis and System Designcited by 47
  7. 2020Blind Federated Edge Learningcited by 43
  8. 2021Context-Aware Online Client Selection for Hierarchical Federated Learningcited by 20
  9. 2023HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Associationcited by 17
  10. 2022Scalable Hierarchical Over-the-Air Federated Learningcited by 14
  11. 2021Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfercited by 10
  12. 2022Over-the-Air Federated Edge Learning with Hierarchical Clusteringcited by 10
8 more
  1. 2023Adaptive Federated Pruning in Hierarchical Wireless Networkscited by 10
  2. 2023Delay-Aware Hierarchical Federated Learningcited by 9
  3. 2023Delay Sensitive Hierarchical Federated Learning with Stochastic Local Updatescited by 8
  4. 2024Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneitycited by 6
  5. 2024Device Scheduling and Assignment in Hierarchical Federated Learning for Internet of Thingscited by 6
  6. 2020The Potential of Multilayered Hierarchical Nonterrestrial Networks for 6G: A Comparative Analysis Among Networking Architecturescited by 4
  7. 2023Optimal Resource Management for Hierarchical Federated Learning over HetNets with Wireless Energy Transfercited by 4
  8. 2024Hierarchical Federated ADMMcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Designcited by 0
  2. 2026From Euclidean to Graph-Structured Data: A Survey of Collaborative Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Hierarchical Federated Learning Approach for the Internet of Things
  2. 2022HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation
  3. 2024FedFQ: Federated Learning with Fine-Grained Quantization
  4. 2023Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation
  5. 2024Quantized and Asynchronous Federated Learning
  6. 2025FedHQ: Hybrid Runtime Quantization for Federated Learning
  7. 2022Communication-Efficient Federated Learning With Data and Client Heterogeneity
  8. 2022Performance Optimization for Variable Bitwidth Federated Learning in Wireless Networks