# Personalized Federated Learning on Tiny-ImageNet Pathological 20 Source: [Personalized Federated Learning on Tiny-ImageNet Pathological 20]() Collection index: [llms.txt]() Data updated: 2026-02-27T06:04:02.681Z Evaluation of Personalized Federated Learning performance on the Tiny-ImageNet dataset configured under the Pathological 20 condition, reporting metrics including accuracy at top 30 (acc@30) and speedup. 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 | Personalized Federated Learning | | Dataset (including any stated split) | Tiny-ImageNet Pathological 20 | | Metric | Top-30 Accuracy | | Unit | SCALAR | | 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 - [Top-30 Accuracy](): Higher is better; unit: SCALAR. - [Speedup](): Higher is better; unit: SCALAR. ## Recorded results | Method | Top-30 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | OSGP | 258 | Not recorded | 68fa5bd71e209131ce9cc033 | | DFedAvgM | 210 | Not recorded | 68fa5bd71e209131ce9cc033 | | Dis-PFL | 188 | Not recorded | 68fa5bd71e209131ce9cc033 | | FedBABU | 181 | Not recorded | 68fa5bd71e209131ce9cc033 | | FedAvg | 172 | Not recorded | 68fa5bd71e209131ce9cc033 | | FedPer | 134 | Not recorded | 68fa5bd71e209131ce9cc033 | | FedRep | 117 | Not recorded | 68fa5bd71e209131ce9cc033 | | DFedPGP | 53 | Not recorded | 68fa5bd71e209131ce9cc033 | ### OSGP Top-30 Accuracy: 258. Result ID: 69a133bb35dfcabb00e57862. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DFedAvgM Top-30 Accuracy: 210. Result ID: 69a133bb35dfcabb00e57861. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Dis-PFL Top-30 Accuracy: 188. Result ID: 69a133bb35dfcabb00e57863. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FedBABU Top-30 Accuracy: 181. Result ID: 69a133bb35dfcabb00e57860. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FedAvg Top-30 Accuracy: 172. Result ID: 69a133bb35dfcabb00e5785d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FedPer Top-30 Accuracy: 134. Result ID: 69a133bb35dfcabb00e5785e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FedRep Top-30 Accuracy: 117. Result ID: 69a133bb35dfcabb00e5785f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DFedPGP Top-30 Accuracy: 53. Result ID: 69a133bb35dfcabb00e57864. [Reporting paper]() [Method origin paper]() 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.