RECORD
Robust softmax aggregation on blockchain based federated learning with convergence guarantee
Cryptography and Security · Submitted 13 Nov 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Our comprehensive experiments show that our framework outperforms existing robust aggregation algorithms in various settings by large margins.
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
Blockchain based federated learning is a distributed learning scheme that allows model training without participants sharing their local data sets, where the blockchain components eliminate the need for a trusted central server compared to traditional Federated Learning algorithms. In this paper we propose a softmax aggregation blockchain based federated learning framework. First, we propose a new blockchain based federated learning architecture that utilizes the well-tested proof-of-stake consensus mechanism on an existing blockchain network to select validators and miners to aggregate the participants' updates and compute the blocks. Second, to ensure the robustness of the aggregation process, we design a novel softmax aggregation method based on approximated population loss values that relies on our specific blockchain architecture. Additionally, we show our softmax aggregation technique converges to the global minimum in the convex setting with non-restricting assumptions. Our comprehensive experiments show that our framework outperforms existing robust aggregation algorithms in various settings by large margins.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Blockchain based federated learning is a distributed learning scheme that allows model training without participants sharing their local data sets, where the blockchain components eliminate the need for a trusted central server compared to traditional Federated Learning algorithms. | background 1.00 | 0.05 | 0.03 | asserted 1.00 |
| s1 | In this paper we propose a softmax aggregation blockchain based federated learning framework. | contribution 1.00 | 0.86 | 0.07 | asserted 0.96 |
| s2 | First, we propose a new blockchain based federated learning architecture that utilizes the well-tested proof-of-stake consensus mechanism on an existing blockchain network to select validators and miners to aggregate the participants' updates and compute the blocks. | method 0.71 | 0.85 | 0.05 | asserted 1.00 |
| s3 | Second, to ensure the robustness of the aggregation process, we design a novel softmax aggregation method based on approximated population loss values that relies on our specific blockchain architecture. | method 0.54 | 0.95 | 0.08 | asserted 1.00 |
| s4 | Additionally, we show our softmax aggregation technique converges to the global minimum in the convex setting with non-restricting assumptions. | result 0.62 | 0.94 | 0.18 | asserted 1.00 |
| s5 | Our comprehensive experiments show that our framework outperforms existing robust aggregation algorithms in various settings by large margins. | result 1.00 | 0.96 | 0.72 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- 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
Blockchain based federated learning is a distributed learning scheme that allows model training without participants sharing their local data sets, where the blockchain components eliminate the need for a trusted central server compared to traditional Federated Learning algorithms. In this paper we propose a softmax aggregation blockchain based federated learning framework. First, we propose a new blockchain based federated learning architecture that utilizes the well-tested proof-of-stake consensus mechanism on an existing blockchain network to select validators and miners to aggregate the participants' updates and compute the blocks. Second, to ensure the robustness of the aggregation process, we design a novel softmax aggregation method based on approximated population loss values that relies on our specific blockchain architecture. Additionally, we show our softmax aggregation technique converges to the global minimum in the convex setting with non-restricting assumptions. Our comprehensive experiments show that our framework outperforms existing robust aggregation algorithms in various settings by large margins.
Human review
References
How the literature uses it
1 arXiv paper cite this in 1 sentence
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.