# Image Classification on CIFAR-100 Cross-Silo, alpha=0.5 Source: [Image Classification on CIFAR-100 Cross-Silo, alpha=0.5]() Collection index: [llms.txt]() Data updated: 2026-06-15T07:50:52.650Z Evaluation of Image Classification performance on the CIFAR-100 dataset configured for Cross-Silo federated learning with a non-IID parameter alpha (α) 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-100 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 | | --- | --- | --- | --- | | FEDSAM + CONST | 39.61 | Not recorded | 6a2f872fd33dfb23e783c0bc | | SCAFFOLD + CONST | 38.93 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDSAM | 38.43 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN + CONST | 37.22 | Not recorded | 6a2f872fd33dfb23e783c0bc | | SCAFFOLD | 37.18 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG + CONST | 36.82 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON + CONST | 36.8 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX + CONST | 36.56 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON | 35.19 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN | 35.07 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX | 34.11 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG | 33.51 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN + CONST | 27.14 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG + CONST | 26.86 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX + CONST | 26.78 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON + CONST | 26.76 | Not recorded | 6a2f872fd33dfb23e783c0bc | | SCAFFOLD + CONST | 26.74 | Not recorded | 6a2f872fd33dfb23e783c0bc | | MOON | 18.72 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDPROX | 18.42 | Not recorded | 6a2f872fd33dfb23e783c0bc | | SCAFFOLD | 17.66 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDAVG | 17.46 | Not recorded | 6a2f872fd33dfb23e783c0bc | | FEDDYN | 16.79 | Not recorded | 6a2f872fd33dfb23e783c0bc | ### FEDSAM + CONST Top-1 Accuracy: 39.61. Result ID: 6a2faec1fbc373592c2bc72c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### SCAFFOLD + CONST Top-1 Accuracy: 38.93. Result ID: 6a2faec1fbc373592c2bc728. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDSAM Top-1 Accuracy: 38.43. Result ID: 6a2faec1fbc373592c2bc72b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDDYN + CONST Top-1 Accuracy: 37.22. Result ID: 6a2faec1fbc373592c2bc72a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### SCAFFOLD Top-1 Accuracy: 37.18. Result ID: 6a2faec1fbc373592c2bc727. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDAVG + CONST Top-1 Accuracy: 36.82. Result ID: 6a2faec1fbc373592c2bc722. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### MOON + CONST Top-1 Accuracy: 36.8. Result ID: 6a2faec1fbc373592c2bc726. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDPROX + CONST Top-1 Accuracy: 36.56. Result ID: 6a2faec1fbc373592c2bc724. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### MOON Top-1 Accuracy: 35.19. Result ID: 6a2faec1fbc373592c2bc725. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDDYN Top-1 Accuracy: 35.07. Result ID: 6a2faec1fbc373592c2bc729. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDPROX Top-1 Accuracy: 34.11. Result ID: 6a2faec1fbc373592c2bc723. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDAVG Top-1 Accuracy: 33.51. Result ID: 6a2faec1fbc373592c2bc721. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction. ### FEDDYN + CONST Top-1 Accuracy: 27.14. Result ID: 6a2faec1fbc373592c2bc720. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDAVG + CONST Top-1 Accuracy: 26.86. Result ID: 6a2faec1fbc373592c2bc718. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDPROX + CONST Top-1 Accuracy: 26.78. Result ID: 6a2faec1fbc373592c2bc71a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### MOON + CONST Top-1 Accuracy: 26.76. Result ID: 6a2faec1fbc373592c2bc71c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### SCAFFOLD + CONST Top-1 Accuracy: 26.74. Result ID: 6a2faec1fbc373592c2bc71e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### MOON Top-1 Accuracy: 18.72. Result ID: 6a2faec1fbc373592c2bc71b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDPROX Top-1 Accuracy: 18.42. Result ID: 6a2faec1fbc373592c2bc719. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### SCAFFOLD Top-1 Accuracy: 17.66. Result ID: 6a2faec1fbc373592c2bc71d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDAVG Top-1 Accuracy: 17.46. Result ID: 6a2faec1fbc373592c2bc717. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LeNet-5"}. This record does not assert independent reproduction. ### FEDDYN Top-1 Accuracy: 16.79. Result ID: 6a2faec1fbc373592c2bc71f. [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.