# Federated Learning Image Classification on DirtyMNIST Source: [Federated Learning Image Classification on DirtyMNIST]() Collection index: [llms.txt]() Data updated: 2026-04-01T08:45:29.492Z Evaluation of Federated Learning Image Classification performance on the DirtyMNIST dataset, reporting classification accuracy and specific federated learning convergence/performance metrics. 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 | Federated Learning Image Classification | | Dataset (including any stated split) | DirtyMNIST | | Metric | Max r\_k(θ) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Max r\_k(θ)](): Higher is better; unit: SCALAR. - [Min r\_k(θ)](): Higher is better; unit: SCALAR. - [Accuracy](): Higher is better; unit: PERCENT. - [Variance of r\_k(θ) across Clients](): Lower is better; unit: SCALAR. ## Recorded results | Method | Max r\_k(θ) | Result date | Report paper | | --- | --- | --- | --- | | EAGLE | 0.434 | Not recorded | 69cca6a20636e5bf4afcbc4a | | EAGLE | 0.322 | Not recorded | 69cca6a20636e5bf4afcbc4a | | EAGLE | -0.002 | Not recorded | 69cca6a20636e5bf4afcbc4a | | AFL | -0.016 | Not recorded | 69cca6a20636e5bf4afcbc4a | | q-FFL | -0.062 | Not recorded | 69cca6a20636e5bf4afcbc4a | | q-FFL | -0.07 | Not recorded | 69cca6a20636e5bf4afcbc4a | | EAGLE | -0.076 | Not recorded | 69cca6a20636e5bf4afcbc4a | | FedAvg | -0.083 | Not recorded | 69cca6a20636e5bf4afcbc4a | | q-FFL | -0.084 | Not recorded | 69cca6a20636e5bf4afcbc4a | | EAGLE | -0.094 | Not recorded | 69cca6a20636e5bf4afcbc4a | | EAGLE | -0.095 | Not recorded | 69cca6a20636e5bf4afcbc4a | | EAGLE | -0.099 | Not recorded | 69cca6a20636e5bf4afcbc4a | ### EAGLE Max r\_k(θ): 0.434. Result ID: 69ccdb1647f34ce924b6a06b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","λ":"5.0"}. This record does not assert independent reproduction. ### EAGLE Max r\_k(θ): 0.322. Result ID: 69ccdb1647f34ce924b6a06a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","λ":"3.0"}. This record does not assert independent reproduction. ### EAGLE Max r\_k(θ): -0.002. Result ID: 69ccdb1647f34ce924b6a069. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","λ":"1.0"}. This record does not assert independent reproduction. ### AFL Max r\_k(θ): -0.016. Result ID: 69ccdb1647f34ce924b6a060. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### q-FFL Max r\_k(θ): -0.062. Result ID: 69ccdb1647f34ce924b6a063. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","q":"3.0"}. This record does not assert independent reproduction. ### q-FFL Max r\_k(θ): -0.07. Result ID: 69ccdb1647f34ce924b6a064. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","q":"5.0"}. This record does not assert independent reproduction. ### EAGLE Max r\_k(θ): -0.076. Result ID: 69ccdb1647f34ce924b6a068. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","λ":"0.7"}. This record does not assert independent reproduction. ### FedAvg Max r\_k(θ): -0.083. Result ID: 69ccdb1647f34ce924b6a061. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### q-FFL Max r\_k(θ): -0.084. Result ID: 69ccdb1647f34ce924b6a062. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","q":"1.0"}. This record does not assert independent reproduction. ### EAGLE Max r\_k(θ): -0.094. Result ID: 69ccdb1647f34ce924b6a067. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","λ":"0.5"}. This record does not assert independent reproduction. ### EAGLE Max r\_k(θ): -0.095. Result ID: 69ccdb1647f34ce924b6a065. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","λ":"0.1"}. This record does not assert independent reproduction. ### EAGLE Max r\_k(θ): -0.099. Result ID: 69ccdb1647f34ce924b6a066. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN","λ":"0.3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.