The DOI matches its Crossref record; 10 of the 12 references it cites were found in a registry or an index.
A Performance Evaluation of Federated Learning Algorithms
Open accessAbstract
Federated learning is an approach to distributed machine learning where a global model is learned by aggregating models that have been trained locally on data-generating clients. Contrary to centralized optimization, clients can be very large in number and face challenges of data and network heterogeneity. Examples of clients include smartphones and connected vehicles, which highlights the practical relevance of federated learning. We benchmark three federated learning algorithms and compare their performance against a centralized approach where data resides on the server. The algorithms Federated Averaging (FedAvg), Federated Stochastic Variance Reduced Gradient, and CO-OP are evaluated on the MNIST dataset, using both i.i.d. and non-i.i.d. partitionings of the data. Our results show that FedAvg achieves the highest accuracy among the federated algorithms, regardless of how data was partitioned. Our comparison between FedAvg and centralized learning shows that they are practically equivalent when i.i.d. data is used. However, the centralized approach outperforms FedAvg with non-i.i.d. data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates.”
From Federated learning enables big data for rare cancer boundary detection (2022) · cites this paper as [18]
In the citing paper
“These algorithms were evaluated on MINIST dataset with the use of non-i.i.d. and i.i.d.partitioning of data.”
From Applications of Federated Learning; Taxonomy, Challenges, and Research Trends (2022) · cites this paper as [125]
In the citing paper
“Nilsson et al. benchmarked three FL algorithms.They compared the performance of these three algorithms by residing the data on the server [125].The algorithms include federated averaging (FedAvg), CO-OP, and Federated-Stochastic Variance Reduced Gradient.”
From Applications of Federated Learning; Taxonomy, Challenges, and Research Trends (2022) · cites this paper as [125]
In the citing paper
“The research resulted in FedAvg as the highest accuracy algorithm among all.”
From Applications of Federated Learning; Taxonomy, Challenges, and Research Trends (2022) · cites this paper as [125]
In the citing paper
“FedAvg achieves the highest accuracy of 98% among these algorithms, regardless of the manner of data partitioning.”
From Applications of Federated Learning; Taxonomy, Challenges, and Research Trends (2022) · cites this paper as [125]
Citations
Cites
(2016) · Cited by 11,679
(2012) · Cited by 8,009
Federated Optimization: Distributed Machine Learning for On-Device Intelligence
Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016) · arXiv · doi:10.48550/arxiv.1610.02527 · Cited by 1,563
Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysisPreprint
Benavoli, A., Giorgio Corani, A., Demšar, J., & Marco Zaffalon, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04316 · Cited by 324
Distance metric learning with eigenvalue optimization
Ying, Y., & Li, P. (2012) · Open Research Exeter (University of Exeter) · Cited by 301
On the Way towards Fourth-Generation Mobile: 3GPP LTE and LTE-Advanced
Martín‐Sacristán, D., Monserrat, J. F., Cabrejas-Peñuelas, J., Calabuig, D., Garrigas, S., & Cardona, N. (2009) · EURASIP Journal on Wireless Communications and Networking · doi:10.1155/2009/354089 · Cited by 169
A Bayesian approach for comparing cross-validated algorithms on multiple data sets
Corani, G., & Benavoli, A. (2015) · Machine Learning · doi:10.1007/s10994-015-5486-z · Cited by 70
Big Automotive Data: Leveraging large volumes of data for knowledge-driven product development
Johanson, M., Belenki, S., Jalminger, J., Fant, M., & Gjertz, M. (2014) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2014.7004298 · Cited by 59
KELP: a Kernel-based Learning Platform
Filice, S., Castellucci, G., Martino, G. D. S., Aless, Moschitti, R., Croce, D., & Basili, R. (2018) · Cineca Institutional Research Information System (Tor Vergata University) · Cited by 48
Is LTE-Advanced really advanced?
Hyun, J., Won, Y., Kim, E., Yoo, J., & Hong, J. W. (2016) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms.2016.7502881 · Cited by 2
Research works printed but not linked: 3
- Hitachi Data Systems . 2015. The Internet on Wheels and Hitachi , Ltd . White Paper. Hitachi Data Systems. 2015. The Internet on Wheels and Hitachi, Ltd. White Paper.
- H Brendan McMahan Eider Moore Daniel Ramage Seth Hampson etal 2016. Communication-efficient learning of deep networks from decentralized data. arXiv:1602.05629 H Brendan McMahan Eider Moore Daniel Ramage Seth Hampson et al. 2016. Communication-efficient learning of deep networks from decentralized data. arXiv:1602.05629 · arXiv
- Yushi Wang . 2017. CO-OP: Cooperative Machine Learning from Mobile Devices. Master's thesis. Dept. Elect. and Comput. Eng ., Univ. Alberta , Edmonton, Canada . Yushi Wang. 2017. CO-OP: Cooperative Machine Learning from Mobile Devices. Master's thesis. Dept. Elect. and Comput. Eng., Univ. Alberta, Edmonton, Canada.
Cited by
Sorted by citations
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3075439 · Cited by 1,503
“Indeed, the well-known FL algorithm FedAvg makes limited assumption that all IoT device clients join in each communication round for FL training [192], which is often not feasible in realistic IoT scenarios due to device connection loss or running out of battery.”
BackgroundA survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., & He, B. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3124599 · Cited by 1,407
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. (2021) · Deakin Research Online (Deakin University) · Cited by 889
Abdulrahman, S., Tout, H., Ould-Slimane, H., Mourad, A., Talhi, C., & Guizani, M. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3030072 · Cited by 796
Metadata
- Authors
- Nilsson, A., Smith, S., Ulm, G., Gustavsson, E., & Jirstrand, M.
- Affiliations
- Fraunhofer Chalmers Research Centre for Industrial Mathematics (SE)
- Venue
- Proceedings of the Second Workshop on Distributed Infrastructures for Deep Learning
- Publisher
- ACM
- Published
- 2018-12-10
- Pages
- 1-8
- OpenAlex
- W2900594532
- Cited by
- 328
- References
- 12
- Citations by year
- 2026: 31 · 2025: 52 · 2024: 80 · 2023: 68 · 2022: 51 · 2021: 24 · 2020: 15 · 2019: 7
- FWCI
- 4.68
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) (submittedVersion)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- Chalmers Research (Chalmers University of Technology) (submittedVersion)
- Funders
- VINNOVA (2016-04260)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- federated learning, FedAvg, co-ops, centralized learning, non-IID data, data heterogeneity, network heterogeneity, MNIST, distributed learning
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
