# Image Classification on CIFAR-100 i.i.d. 500 clients 2% participation (test)

Source: [Image Classification on CIFAR-100 i.i.d. 500 clients 2% participation (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-i-i-d-500-clients-2-percent-participation-test>)

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

Data updated: 2026-02-27T09:04:33.068Z

Evaluation of Image Classification performance on the CIFAR-100 test set under a specific federated setting: IID data partitioning across 500 clients, where each client holds 2% of the data. Metrics tracked include Accuracy and communication Rounds.

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) | CIFAR-100 i.i.d. 500 clients 2% participation (test) |
| Metric | Accuracy (500R) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Accuracy (500R)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-i-i-d-500-clients-2-percent-participation-test.md?metric=Accuracy%20(500R)>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-i-i-d-500-clients-2-percent-participation-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Communication Rounds](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-i-i-d-500-clients-2-percent-participation-test.md?metric=Communication%20Rounds>): Lower is better; unit: SCALAR.

- [Accuracy (1000R)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-i-i-d-500-clients-2-percent-participation-test.md?metric=Accuracy%20(1000R)>): Higher is better; unit: PERCENT.

- [Communication Rounds (33%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-i-i-d-500-clients-2-percent-participation-test.md?metric=Communication%20Rounds%20(33%25)>): Lower is better; unit: SCALAR.

- [Communication Rounds (42%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-i-i-d-500-clients-2-percent-participation-test.md?metric=Communication%20Rounds%20(42%25)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy (500R) | Result date | Report paper |
| --- | --- | --- | --- |
| FedACG | 41.16 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedADAM | 38.74 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedMLB | 34.56 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedDC‡ | 33.93 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedAvgM | 33.54 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedDyn | 33.2 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedAvg | 30.71 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedDecorr | 30.41 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedProx | 30.11 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedNTD | 30.04 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedLC | 29.91 | Not recorded | 68fa72b01e209131cea57eb7 |
| FedCM† | 29.59 | Not recorded | 68fa72b01e209131cea57eb7 |
| MOON | 28.82 | Not recorded | 68fa72b01e209131cea57eb7 |

### FedACG

Accuracy (500R): 41.16. Result ID: 69a15e1b35dfcabb00e69600.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Implementation](<https://github.com/ninigapa0/FedAGM>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedADAM

Accuracy (500R): 38.74. Result ID: 69a15e1b35dfcabb00e695f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa58711e209131ce9ae27a.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedMLB

Accuracy (500R): 34.56. Result ID: 69a15e1b35dfcabb00e695fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d031e209131cea3754a.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedDC‡

Accuracy (500R): 33.93. Result ID: 69a15e1b35dfcabb00e695fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b80.md>)

[Implementation](<https://github.com/gaoliang13/FedDC>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedAvgM

Accuracy (500R): 33.54. Result ID: 69a15e1b35dfcabb00e695f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66581e209131cea0faa1.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedDyn

Accuracy (500R): 33.2. Result ID: 69a15e1b35dfcabb00e695f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b361e209131cea2cecf.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedAvg

Accuracy (500R): 30.71. Result ID: 69a15e1b35dfcabb00e695f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

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

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedDecorr

Accuracy (500R): 30.41. Result ID: 69a15e1b35dfcabb00e695ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d61e209131cea58d02.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedProx

Accuracy (500R): 30.11. Result ID: 69a15e1b35dfcabb00e695f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67701e209131cea163fe.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedNTD

Accuracy (500R): 30.04. Result ID: 69a15e1b35dfcabb00e695fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7a5.md>)

[Implementation](<https://github.com/Lee-Gihun/FedNTD>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedLC

Accuracy (500R): 29.91. Result ID: 69a15e1b35dfcabb00e695fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d851e209131cea3a601.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### FedCM†

Accuracy (500R): 29.59. Result ID: 69a15e1b35dfcabb00e695fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3d1e209131cea26ed8.md>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

### MOON

Accuracy (500R): 28.82. Result ID: 69a15e1b35dfcabb00e695f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fca.md>)

[Implementation](<https://github.com/QinbinLi/MOON>)

Recorded evaluation configuration: {"clients":"500","participation":"2%","data\_distribution":"i.i.d."}. This record does not assert independent reproduction.

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