RECORD
On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing
Machine Learning · Submitted 19 Mar 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Theoretical and experimental results demonstrate that under imperfect information sharing, the third scheme that mixes gradients is more robust in the presence of a noisy channel compared with the algorithms from the literature that mix the parameters.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Decentralized learning and optimization is a central problem in control that encompasses several existing and emerging applications, such as federated learning. While there exists a vast literature on this topic and most methods centered around the celebrated average-consensus paradigm, less attention has been devoted to scenarios where the communication between the agents may be imperfect. To this end, this paper presents three different algorithms of Decentralized Federated Learning (DFL) in the presence of imperfect information sharing modeled as noisy communication channels. The first algorithm, Federated Noisy Decentralized Learning (FedNDL1), comes from the literature, where the noise is added to their parameters to simulate the scenario of the presence of noisy communication channels. This algorithm shares parameters to form a consensus with the clients based on a communication graph topology through a noisy communication channel. The proposed second algorithm (FedNDL2) is similar to the first algorithm but with added noise to the parameters, and it performs the gossip averaging before the gradient optimization. The proposed third algorithm (FedNDL3), on the other hand, shares the gradients through noisy communication channels instead of the parameters. Theoretical and experimental results demonstrate that under imperfect information sharing, the third scheme that mixes gradients is more robust in the presence of a noisy channel compared with the algorithms from the literature that mix the parameters.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Decentralized learning and optimization is a central problem in control that encompasses several existing and emerging applications, such as federated learning. | background 1.00 | 0.04 | 0.01 | asserted 1.00 |
| s1 | While there exists a vast literature on this topic and most methods centered around the celebrated average-consensus paradigm, less attention has been devoted to scenarios where the communication between the agents may be imperfect. | gap 0.89 | 0.05 | 0.02 | asserted 0.98 |
| s2 | To this end, this paper presents three different algorithms of Decentralized Federated Learning (DFL) in the presence of imperfect information sharing modeled as noisy communication channels. | contribution 1.00 | 0.87 | 0.04 | asserted 0.99 |
| s3 | The first algorithm, Federated Noisy Decentralized Learning (FedNDL1), comes from the literature, where the noise is added to their parameters to simulate the scenario of the presence of noisy communication channels. | method 0.73 | 0.07 | 0.02 | asserted 1.00 |
| s4 | This algorithm shares parameters to form a consensus with the clients based on a communication graph topology through a noisy communication channel. | method 0.92 | 0.09 | 0.02 | asserted 1.00 |
| s5 | The proposed second algorithm (FedNDL2) is similar to the first algorithm but with added noise to the parameters, and it performs the gossip averaging before the gradient optimization. | method 0.82 | 0.76 | 0.02 | asserted 0.99 |
| s6 | The proposed third algorithm (FedNDL3), on the other hand, shares the gradients through noisy communication channels instead of the parameters. | method 0.82 | 0.60 | 0.05 | asserted 0.97 |
| s7 | Theoretical and experimental results demonstrate that under imperfect information sharing, the third scheme that mixes gradients is more robust in the presence of a noisy channel compared with the algorithms from the literature that mix the parameters. | result 0.97 | 0.95 | 0.93 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Decentralized learning and optimization is a central problem in control that encompasses several existing and emerging applications, such as federated learning. While there exists a vast literature on this topic and most methods centered around the celebrated average-consensus paradigm, less attention has been devoted to scenarios where the communication between the agents may be imperfect. To this end, this paper presents three different algorithms of Decentralized Federated Learning (DFL) in the presence of imperfect information sharing modeled as noisy communication channels. The first algorithm, Federated Noisy Decentralized Learning (FedNDL1), comes from the literature, where the noise is added to their parameters to simulate the scenario of the presence of noisy communication channels. This algorithm shares parameters to form a consensus with the clients based on a communication graph topology through a noisy communication channel. The proposed second algorithm (FedNDL2) is similar to the first algorithm but with added noise to the parameters, and it performs the gossip averaging before the gradient optimization. The proposed third algorithm (FedNDL3), on the other hand, shares the gradients through noisy communication channels instead of the parameters. Theoretical and experimental results demonstrate that under imperfect information sharing, the third scheme that mixes gradients is more robust in the presence of a noisy channel compared with the algorithms from the literature that mix the parameters.
Human review
How the literature uses it
5 arXiv papers cite this in 5 sentences
What it cites · 2 sentences without a confident label
Cites as background 1 paper
-
This led to an advancement in decentralized optimization algorithms [ref] such as the Decentralized Federated Learning (DFL) [ref] and Federated Learning (FL) [ref] where only weights or gradients are transferred instead of the raw data from all agents involved.
Federated Learning: Strategies for Improving Communication Efficiency · Introduction · 0.95
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.