# Image Classification on CIFAR-10 Cross-Silo (alpha=0.5) Source: [Image Classification on CIFAR-10 Cross-Silo (alpha=0.5)]() Collection index: [llms.txt]() Data updated: 2026-06-15T07:50:52.615Z Evaluation of Image Classification performance on the CIFAR-10 dataset configured for Cross-Silo federated learning with a non-IID parameter alpha set to 0.5. 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-10 Cross-Silo, alpha=0.5 | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 22 of 22 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SCAFFOLD + CONST | 75.09 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDSAM + CONST | 72.64 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG + CONST | 72.44 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX + CONST | 71.96 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON + CONST | 71.84 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN + CONST | 71.76 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDSAM | 69.45 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON | 68.45 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN | 65.5 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX | 64.51 | Not recorded | 6a2f872fd33dfb23e783c0bc | | SCAFFOLD | 64.5 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG | 64.25 | Not recorded | 6a2f872fd33dfb23e783c0bc | | SCAFFOLD + CONST | 63.03 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX + CONST | 60.7 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON + CONST | 59.86 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN + CONST | 59.76 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG + CONST | 59.66 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON | 55.79 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX | 55.15 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG | 53.12 | Not recorded | 6a2f872fd33dfb23e783c0bc | | SCAFFOLD | 52.74 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN | 51.05 | Not recorded | 6a2f872fd33dfb23e783c0bc | ### SCAFFOLD + CONST Top-1 Accuracy: 75.09. Result ID: 6a2faec1fbc373592c2bc712. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDSAM + CONST Top-1 Accuracy: 72.64. Result ID: 6a2faec1fbc373592c2bc716. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDAVG + CONST Top-1 Accuracy: 72.44. Result ID: 6a2faec1fbc373592c2bc70c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDPROX + CONST Top-1 Accuracy: 71.96. Result ID: 6a2faec1fbc373592c2bc70e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### MOON + CONST Top-1 Accuracy: 71.84. Result ID: 6a2faec1fbc373592c2bc710. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDDYN + CONST Top-1 Accuracy: 71.76. Result ID: 6a2faec1fbc373592c2bc714. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDSAM Top-1 Accuracy: 69.45. Result ID: 6a2faec1fbc373592c2bc715. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### MOON Top-1 Accuracy: 68.45. Result ID: 6a2faec1fbc373592c2bc70f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDDYN Top-1 Accuracy: 65.5. Result ID: 6a2faec1fbc373592c2bc713. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDPROX Top-1 Accuracy: 64.51. Result ID: 6a2faec1fbc373592c2bc70d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### SCAFFOLD Top-1 Accuracy: 64.5. Result ID: 6a2faec1fbc373592c2bc711. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDAVG Top-1 Accuracy: 64.25. Result ID: 6a2faec1fbc373592c2bc70b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### SCAFFOLD + CONST Top-1 Accuracy: 63.03. Result ID: 6a2faec1fbc373592c2bc708. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDPROX + CONST Top-1 Accuracy: 60.7. Result ID: 6a2faec1fbc373592c2bc704. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### MOON + CONST Top-1 Accuracy: 59.86. Result ID: 6a2faec1fbc373592c2bc706. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDDYN + CONST Top-1 Accuracy: 59.76. Result ID: 6a2faec1fbc373592c2bc70a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDAVG + CONST Top-1 Accuracy: 59.66. Result ID: 6a2faec1fbc373592c2bc702. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### MOON Top-1 Accuracy: 55.79. Result ID: 6a2faec1fbc373592c2bc705. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDPROX Top-1 Accuracy: 55.15. Result ID: 6a2faec1fbc373592c2bc703. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDAVG Top-1 Accuracy: 53.12. Result ID: 6a2faec1fbc373592c2bc701. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### SCAFFOLD Top-1 Accuracy: 52.74. Result ID: 6a2faec1fbc373592c2bc707. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDDYN Top-1 Accuracy: 51.05. Result ID: 6a2faec1fbc373592c2bc709. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.