# Image Classification on CIFAR10 (Test Accuracy and Communication Efficiency)

Source: [Image Classification on CIFAR10 (Test Accuracy and Communication Efficiency)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-accuracy-and-communication-efficiency>)

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

Data updated: 2026-03-06T09:18:55.408Z

Evaluation of Image Classification performance on the CIFAR-10 dataset, reporting standard test accuracy alongside metrics related to communication efficiency or convergence time required to achieve a specific accuracy threshold (e.g., 70%).

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) | CIFAR10 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-accuracy-and-communication-efficiency.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Communication Time (Days) to 70% Acc](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-accuracy-and-communication-efficiency.md?metric=Communication%20Time%20(Days)%20to%2070%25%20Acc>): Lower is better; unit: TIME.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| QSGD\[2\]+FedBCGD+ | 83.2 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| QSGD\[2\]+FedBCGD | 82.6 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedBCGD+ | 80.6 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedBCGD | 77.2 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedPAQ | 75.2 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| TOP-k | 74.5 | Not recorded | 69aa5f8f2d603e6de3e41917 |
| FedAvg | 73.2 | Not recorded | 69aa5f8f2d603e6de3e41917 |

### QSGD\[2\]+FedBCGD+

Accuracy: 83.2. Result ID: 69aa9ba66dbb7075b95497bc.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

Recorded evaluation configuration: {"Backbone":"LeNet-5","Heterogeneity (ρ)":"0.6","Number of clients (N)":"5","Total communication floats budget":"200d"}. This record does not assert independent reproduction.

### QSGD\[2\]+FedBCGD

Accuracy: 82.6. Result ID: 69aa9ba66dbb7075b95497bb.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

Recorded evaluation configuration: {"Backbone":"LeNet-5","Heterogeneity (ρ)":"0.6","Number of clients (N)":"5","Total communication floats budget":"200d"}. This record does not assert independent reproduction.

### FedBCGD+

Accuracy: 80.6. Result ID: 69aa9ba66dbb7075b95497ba.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

Recorded evaluation configuration: {"Backbone":"LeNet-5","Heterogeneity (ρ)":"0.6","Number of clients (N)":"5","Total communication floats budget":"200d"}. This record does not assert independent reproduction.

### FedBCGD

Accuracy: 77.2. Result ID: 69aa9ba66dbb7075b95497b9.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

Recorded evaluation configuration: {"Backbone":"LeNet-5","Heterogeneity (ρ)":"0.6","Number of clients (N)":"5","Total communication floats budget":"200d"}. This record does not assert independent reproduction.

### FedPAQ

Accuracy: 75.2. Result ID: 69aa9ba66dbb7075b95497b8.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa56ff1e209131ce9a16fa.md>)

Recorded evaluation configuration: {"Backbone":"LeNet-5","Heterogeneity (ρ)":"0.6","Number of clients (N)":"5","Total communication floats budget":"200d"}. This record does not assert independent reproduction.

### TOP-k

Accuracy: 74.5. Result ID: 69aa9ba66dbb7075b95497b7.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b501e209131cea2d95b.md>)

Recorded evaluation configuration: {"Backbone":"LeNet-5","Heterogeneity (ρ)":"0.6","Number of clients (N)":"5","Total communication floats budget":"200d"}. This record does not assert independent reproduction.

### FedAvg

Accuracy: 73.2. Result ID: 69aa9ba66dbb7075b95497b6.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8f2d603e6de3e41917.md>)

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

Recorded evaluation configuration: {"Backbone":"LeNet-5","Heterogeneity (ρ)":"0.6","Number of clients (N)":"5","Total communication floats budget":"200d"}. This record does not assert independent reproduction.

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