# Federated Image Classification on MNIST non-IID, α=0.1 (test)

Source: [Federated Image Classification on MNIST non-IID, α=0.1 (test)](<https://www.sota2.com/research/sota/federated-image-classification-on-mnist-non-iid-0-1-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-28T09:32:45.880Z

Evaluation of Federated Image Classification performance on the MNIST test set under a specific non-IID distribution characterized by alpha=0.1.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Federated Image Classification |
| Dataset (including any stated split) | MNIST non-IID, α=0.1 (test) |
| Metric | Test Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Test Accuracy](<https://www.sota2.com/research/sota/federated-image-classification-on-mnist-non-iid-0-1-test.md?metric=Test%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Test Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FedAvg-M | 95.51 | Not recorded | 69f03f2d55a3c32af89fa1b7 |
| FedSLoP | 95.11 | Not recorded | 69f03f2d55a3c32af89fa1b7 |
| FedLoRA-M | 92.47 | Not recorded | 69f03f2d55a3c32af89fa1b7 |
| FedMef | 89.65 | Not recorded | 69f03f2d55a3c32af89fa1b7 |
| NeuLite | 89.23 | Not recorded | 69f03f2d55a3c32af89fa1b7 |
| FederatedSelect | 87.59 | Not recorded | 69f03f2d55a3c32af89fa1b7 |

### FedAvg-M

Test Accuracy: 95.51. Result ID: 69f07eac47f34ce924d6c40d.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2d55a3c32af89fa1b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e761e209131cea40072.md>)

Recorded evaluation configuration: {"Compression ratio":"1","Communication rounds (T)":"100","Dirichlet concentration (α)":"0.1","Number of clients (p)":"50","Local epochs per round":"1","Mini-batch size (b)":"32","Global step-size (η)":"0.018"}. This record does not assert independent reproduction.

### FedSLoP

Test Accuracy: 95.11. Result ID: 69f07eac47f34ce924d6c412.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2d55a3c32af89fa1b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f2d55a3c32af89fa1b7.md>)

Recorded evaluation configuration: {"Compression ratio":"1/7","Communication rounds (T)":"100","Dirichlet concentration (α)":"0.1","Number of clients (p)":"50","Local epochs per round":"1","Mini-batch size (b)":"32","Global step-size (η)":"0.018","FedSLoP projection rank r":"112","FedSLoP momentum":"0.8"}. This record does not assert independent reproduction.

### FedLoRA-M

Test Accuracy: 92.47. Result ID: 69f07eac47f34ce924d6c411.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2d55a3c32af89fa1b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Compression ratio":"1/7","Communication rounds (T)":"100","Dirichlet concentration (α)":"0.1","Number of clients (p)":"50","Local epochs per round":"1","Mini-batch size (b)":"32","Global step-size (η)":"0.018","LoRA rank":"15"}. This record does not assert independent reproduction.

### FedMef

Test Accuracy: 89.65. Result ID: 69f07eac47f34ce924d6c40e.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2d55a3c32af89fa1b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a01e209131cea57a20.md>)

Recorded evaluation configuration: {"Compression ratio":"1/7","Communication rounds (T)":"100","Dirichlet concentration (α)":"0.1","Number of clients (p)":"50","Local epochs per round":"1","Mini-batch size (b)":"32","Global step-size (η)":"0.018"}. This record does not assert independent reproduction.

### NeuLite

Test Accuracy: 89.23. Result ID: 69f07eac47f34ce924d6c40f.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2d55a3c32af89fa1b7.md>)

Recorded evaluation configuration: {"Compression ratio":"1/7","Communication rounds (T)":"100","Dirichlet concentration (α)":"0.1","Number of clients (p)":"50","Local epochs per round":"1","Mini-batch size (b)":"32","Global step-size (η)":"0.018"}. This record does not assert independent reproduction.

### FederatedSelect

Test Accuracy: 87.59. Result ID: 69f07eac47f34ce924d6c410.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f2d55a3c32af89fa1b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d391e209131cea388cd.md>)

Recorded evaluation configuration: {"Compression ratio":"1/7","Communication rounds (T)":"100","Dirichlet concentration (α)":"0.1","Number of clients (p)":"50","Local epochs per round":"1","Mini-batch size (b)":"32","Global step-size (η)":"0.018"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.