# Image Classification on MNIST (test) (Federated Learning Fairness and Client Variance)

Source: [Image Classification on MNIST (test) (Federated Learning Fairness and Client Variance)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance>)

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

Data updated: 2026-02-26T05:51:53.207Z

Evaluation of Image Classification performance on the MNIST test set, focusing on fairness and performance variance across participating clients, including metrics like Jain's Fairness Index and worst-client accuracy.

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 | Image Classification |
| Dataset (including any stated split) | MNIST (test) |
| Metric | Mean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Mean Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance.md?metric=Mean%20Accuracy>): Higher is better; unit: PERCENT.

- [Std Dev](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance.md?metric=Std%20Dev>): Lower is better; unit: SCALAR.

- [Min Acc (Worst Client)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance.md?metric=Min%20Acc%20(Worst%20Client)>): Higher is better; unit: PERCENT.

- [Acc Gap (Max-Min)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance.md?metric=Acc%20Gap%20(Max-Min)>): Lower is better; unit: PERCENT.

- [Jain's Fairness Index](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance.md?metric=Jain%27s%20Fairness%20Index>): Higher is better; unit: SCALAR.

- [Avg Acc (Bottom 10%)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance.md?metric=Avg%20Acc%20(Bottom%2010%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SOFA-FL | 98.18 | Not recorded | 6938febc6cfd488761a53ee0 |
| HypCluster | 88.73 | Not recorded | 6938febc6cfd488761a53ee0 |

### SOFA-FL

Mean Accuracy: 98.18. Result ID: 699978345698665ec4e72999.

[Reporting paper](<https://www.sota2.com/research/paper/6938febc6cfd488761a53ee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6938febc6cfd488761a53ee0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HypCluster

Mean Accuracy: 88.73. Result ID: 699978345698665ec4e7299a.

[Reporting paper](<https://www.sota2.com/research/paper/6938febc6cfd488761a53ee0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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