Chain FL: Decentralized Federated Machine Learning via Blockchain
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Federated learning is a collaborative machine learning mechanism that allows multiple parties to develop a model without sharing the training data. It is a promising mechanism since it empowers collaboration in fields such as medicine and banking where data sharing is not favorable due to legal, technical, ethical, or safety issues without significantly sacrificing accuracy. In centralized federated learning, there is a single central server, and hence it has a single point of failure. Unlike centralized federated learning, decentralized federated learning does not depend on a single central server for the updates. In this paper, we propose a decentralized federated learning approach named Chain FL that makes use of the blockchain to delegate the responsibility of storing the model to the nodes on the network instead of a centralized server. Chain FL produced promising results on the MNIST digit recognition task with a maximum 0.20% accuracy decrease, and on the CIFAR-10 image classification task with a maximum of 2.57% accuracy decrease as compared to non-FL counterparts.
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
“SL, however, offers a solution to the governance problem, providing a true collaborative and democratic approach in which partners communicate and work on the same level, jointly and equally training models and sharing the benefits 25,26,33 .”
From Swarm learning for decentralized artificial intelligence in cancer histopathology (2022) · cites this paper as [33]
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“The model we used for this experiment is similar to a VGGNet architecture without the full dense hidden layers at the end, together with Batch Normalization, L2 regularization and Dropout [9].”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“This is trained with Negative Log Likelihood loss, and optimized with AdamW variant of the Adam optimizer, with learning rate 0.001, betas 0.9 and 0.999, and weight decay of 0.01 for L2 regularization [10], [11].”
MethodInfluentialLearning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 12×
“Equation 1: Online Federated Averaging update step where w i denotes current weights of trained model after i th averaging step, n i denotes the total number of unique data points used to train the current model at i th step, w ∗ i denotes weights of the locally trained model, o ∗ i denotes the number of data points t…”
BackgroundMethodInfluentialDecoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
Gossip-based computation of aggregate information
Kempe, D., Dobra, A., & Gehrke, J. (2004) · 44th Annual IEEE Symposium on Foundations of Computer Science, 2003. Proceedings. · doi:10.1109/sfcs.2003.1238221 · Cited by 1,480 · cited 1×
“Other fully decentralized algorithms could also be implemented, like Gossip Aggregation algorithms for sharing the model between parties in the training phase [16], [17].”
MethodBlockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT
Lu, Y., Huang, X., Dai, Y., Maharjan, S., & Zhang, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2942190 · Cited by 1,245 · cited 3×
“A custom blockchain implementation is one of the promising solutions to this [3], [7].”
BackgroundBlockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2020) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2921755 · Cited by 887 · cited 1×
“One of these approaches by Kim et al . is to store a global model on the Blockchain and its miners and update it based on the local updates provided from the collaborators [5].”
BackgroundBlockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2018) · arXiv · doi:10.48550/arxiv.1808.03949 · Cited by 882 · cited 1×
“One of these approaches by Kim et al . is to store a global model on the Blockchain and its miners and update it based on the local updates provided from the collaborators [5].”
Background
Cited by
Swarm learning for decentralized artificial intelligence in cancer histopathology
Saldanha, O. L., Quirke, P., West, N. P., James, J. A., Loughrey, M. B., Grabsch, H. I., Salto-Tellez, M., Alwers, E., Cifci, D., Ghaffari Laleh, N., et al. (2022) · Nature Medicine · doi:10.1038/s41591-022-01768-5 · Cited by 227
Li, D., Han, D., Weng, T.-H., Zheng, Z., Li, H., Liu, H., Castiglione, A., & Li, K.-C. (2022) · Soft Computing · doi:10.1007/s00500-021-06496-5 · Cited by 201
“ChainFL proposed in Korkmaz et al. (2020) achieves encouraging results on the Modified National Institute of Standards and Technology database digit recognition task ( MNIST ) and Canadian Institute for Advanced Research image classifi-cation task ( CIFAR-10 ).”
MethodA Survey of Blockchain and Artificial Intelligence for 6G Wireless Communications
Zuo, Y., Guo, J., Gao, N., Zhu, Y., Jin, S., & Li, X. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3315374 · Cited by 192
“In response to the single point of failure problem of federated learning (FL), the work in [171] provided a decentralized FL scheme entitled ChainFL.”
BackgroundMethodSecuring federated learning with blockchain: a systematic literature review
Qammar, A., Karim, A., Ning, H., & Ding, J. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10271-9 · Cited by 174
“Additionally, other frameworks such as Baffle (Ramanan and Nakayama 2020) and ChainFL (Korkmaz et al. 2020) run on”
MethodDrones’ Edge Intelligence Over Smart Environments in B5G: Blockchain and Federated Learning Synergy
Alsamhi, S. H., Almalki, F. A., Afghah, F., Hawbani, A., Shvetsov, A. V., Lee, B., & Song, H. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3132561 · Cited by 139
“Such Chain FL is used to store and update aggregation of the model [84].”
Metadata
- Authors
- Korkmaz, C., Kocas, H. E., Uysal, A., Masry, A., Ozkasap, O., & Akgun, B.
- Affiliations
- Koç University (TR)
- ORCID
- Korkmaz, Caner
- Venue
- 2020 Second International Conference on Blockchain Computing and Applications (BCCA)
- Publisher
- IEEE
- Published
- 2020-11-02
- Pages
- 140-146
- OpenAlex
- W3112310000
- Cited by
- 84
- References
- 19
- Citations by year
- 2026: 3 · 2025: 13 · 2024: 21 · 2023: 18 · 2022: 19 · 2021: 10
- FWCI
- 4.48
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Conference on Blockchain Computing and Applications (BCCA) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- decentralized federated learning, blockchain, data privacy, single point of failure, MNIST classification
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Chain FL: Decentralized Federated Machine Learning via Blockchain. https://app.cochat.ai/papers/10.1109/bcca50787.2020.9274451
- The paper
- Korkmaz, C., Kocas, H. E., Uysal, A., Masry, A., Ozkasap, O., & Akgun, B. (2020). Chain FL: Decentralized Federated Machine Learning via Blockchain. 2020 Second International Conference on Blockchain Computing and Applications (BCCA). https://doi.org/10.1109/bcca50787.2020.9274451
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.