mlsanityData to 14 Oct 2026

Timely Asynchronous Hierarchical Federated Learning: Age of Convergence

arXiv 2306.12400 ↗First posted 21 Jun 2023cs.IT cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We consider an asynchronous hierarchical federated learning (AHFL) setting with a client-edge-cloud framework. The clients exchange the trained parameters with their corresponding edge servers, which update the locally aggregated model. This model is then transmitted to all the clients in the local cluster. The edge servers communicate to the central cloud server for global model aggregation. The goal of each client is to converge to the global model, while maintaining timeliness of the clients, i.e., having optimum training iteration time. We investigate the convergence criteria for such a system with dense clusters. Our analysis shows that for a system of n clients with fixed average timeliness, the convergence in finite time is probabilistically guaranteed, if the nodes are divided into O(1) number of clusters, that is, if the system is built as a sparse set of edge servers with dense client bases each.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 51 references that are in the map. First posted on arXiv 21 Jun 2023.

Builds on

10 of 51 references.

References · 10

  1. 2018Federated Learning with Non-IID Datacited by 1,108
  2. 2019Asynchronous Federated Optimizationcited by 267
  3. 2022FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learningcited by 17
  4. 2022Federated Learning with Flexible Controlcited by 12
  5. 2020Communication Efficient Federated Learning over Multiple Access Channelscited by 11
  6. 2021Communication-Efficient Federated Learning with Dual-Side Low-Rank Compressioncited by 10
  7. 2023Delay Sensitive Hierarchical Federated Learning with Stochastic Local Updatescited by 8
  8. 2022Asynchronous Hierarchical Federated Learningcited by 4
  9. 2018Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encodingcited by 2
  10. 2023Timely Tracking of a Remote Dynamic Source Via Multi-Hop Renewal Updatescited by 1

Built on by

Not cited yet.