# Image Classification on CIFAR-100 Noisy 100 clients (test)

Source: [Image Classification on CIFAR-100 Noisy 100 clients (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-noisy-100-clients-test>)

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

Data updated: 2026-02-26T06:01:52.429Z

Evaluation of Image Classification performance on the noisy variant of the CIFAR-100 dataset, specifically using the test set distributed across 100 clients.

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 Noisy 100 clients (test) |
| Metric | Relative Accuracy Decrease (%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Relative Accuracy Decrease (%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-noisy-100-clients-test.md?metric=Relative%20Accuracy%20Decrease%20(%25)>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Relative Accuracy Decrease (%) | Result date | Report paper |
| --- | --- | --- | --- |
| FedU | -2.8 | Not recorded | 68fa6b1c1e209131cea2c476 |
| pFedGP | -19.2 | Not recorded | 68fa6b1c1e209131cea2c476 |
| pFedGP-IP-compute | -21.2 | Not recorded | 68fa6b1c1e209131cea2c476 |
| pFedGP-IP-data | -23.1 | Not recorded | 68fa6b1c1e209131cea2c476 |
| pFedHN | -25.7 | Not recorded | 68fa6b1c1e209131cea2c476 |
| LG-FedAvg | -28.3 | Not recorded | 68fa6b1c1e209131cea2c476 |
| pFedme | -30.4 | Not recorded | 68fa6b1c1e209131cea2c476 |
| FedPer | -35.6 | Not recorded | 68fa6b1c1e209131cea2c476 |

### FedU

Relative Accuracy Decrease (%): -2.8. Result ID: 698e5f85ffc3901de09d0c05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da51e209131cea3b20a.md>)

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

### pFedGP

Relative Accuracy Decrease (%): -19.2. Result ID: 698e5f85ffc3901de09d0c09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Implementation](<https://github.com/IdanAchituve/pFedGP>)

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

### pFedGP-IP-compute

Relative Accuracy Decrease (%): -21.2. Result ID: 698e5f85ffc3901de09d0c08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Implementation](<https://github.com/IdanAchituve/pFedGP>)

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

### pFedGP-IP-data

Relative Accuracy Decrease (%): -23.1. Result ID: 698e5f85ffc3901de09d0c07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Implementation](<https://github.com/IdanAchituve/pFedGP>)

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

### pFedHN

Relative Accuracy Decrease (%): -25.7. Result ID: 698e5f85ffc3901de09d0c06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69701e209131cea2212b.md>)

[Implementation](<https://github.com/AvivSham/pFedHN>)

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

### LG-FedAvg

Relative Accuracy Decrease (%): -28.3. Result ID: 698e5f85ffc3901de09d0c03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e81e209131cea190ee.md>)

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

### pFedme

Relative Accuracy Decrease (%): -30.4. Result ID: 698e5f85ffc3901de09d0c04.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ba21e209131cea2f6fd.md>)

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

### FedPer

Relative Accuracy Decrease (%): -35.6. Result ID: 698e5f85ffc3901de09d0c02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1c1e209131cea2c476.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cb1e209131cea12528.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.