Hierarchical Federated Learning ACROSS Heterogeneous Cellular Networks
Open accessAbstract
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.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
IONN divides a DL model into multiple partitions and uploads them sequentially, allowing the edge node to incrementally build the DL model and execute offloaded partial DL computation before the entire model is uploaded.
“IONN divides a DL model, prepared for uploading, into multiple partitions, and uploads them to the edge node in sequential.The edge node, receiving the partitioned models, incrementally builds the DL model as each partitioned model arrives, while being able to execute the offloaded partial DL computation even before the entire DL model is uploaded.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [175]
Unnecessary DNN layers that cannot bring any performance increase are not uploaded, avoiding offloading.
“unnecessary DNN layers, which cannot bring in any performance increase, are not uploaded and hence avoiding the offloading.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [175]
DNN layers with high performance benefit and low uploading overhead are preferred to be uploaded first to quickly build a partial DNN and achieve best-expected query performance.
“DNN layers, performance benefit and uploading overhead of which are high and low, respectively, are preferred to be uploaded first, and thus making the edge node quickly build a partial DNN to achieve the best-expected query performance.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [175]
The citation lists haven’t been fetched yet
References 33 · Cited by 424
- Authors
- Abad, M. S. H., Ozfatura, E., GUndUz, D., & Ercetin, O.
- Affiliations
- Sabancı Üniversitesi (TR)
- ORCID
- Abad, M. S. H.
- Venue
- ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2020-05
- Pages
- 8866-8870
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2972051725
- Cited by
- 424
- References
- 33
- Citations by year
- 2026: 40 · 2025: 72 · 2024: 67 · 2023: 72 · 2022: 79 · 2021: 58 · 2020: 36
- FWCI
- 23.40
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion, cc-by)
- arXiv (Cornell University)
- IEEE RESOURCE CENTERS
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced MIMO Systems Optimization
- Keywords
- federated edge learning, hierarchical federated learning, heterogeneous cellular networks, small cells, mobile base stations, resource allocation, communication delay, model updating, cell-edge users
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
