# Image Classification on Fashion-MNIST heterogeneous (test) Source: [Image Classification on Fashion-MNIST heterogeneous (test)]() Collection index: [llms.txt]() Data updated: 2026-03-04T17:57:59.112Z Evaluation of Image Classification performance on the heterogeneous test split of the Fashion-MNIST dataset, focusing on accuracy and negative log-likelihood. 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) | Fashion-MNIST heterogeneous (test) | | Metric | Test Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Test Accuracy](): Higher is better; unit: PERCENT. - [Test NLL](): Lower is better; unit: SCALAR. ## Recorded results | Method | Test Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FedLap-Cov | 83 | Not recorded | 68fa5da71e209131ce9dbecb | | IVON-ADMM | 83 | Not recorded | 68fa5da71e209131ce9dbecb | | IVON-ADMM@mg | 82.9 | Not recorded | 68fa5da71e209131ce9dbecb | | FedLap | 82.4 | Not recorded | 68fa5da71e209131ce9dbecb | | IVON-ADMM | 82.3 | Not recorded | 68fa5da71e209131ce9dbecb | | FedDyn | 82.2 | Not recorded | 68fa5da71e209131ce9dbecb | | IVON-ADMM@mg | 82.2 | Not recorded | 68fa5da71e209131ce9dbecb | | FedAvg/FedProx | 81.8 | Not recorded | 68fa5da71e209131ce9dbecb | | FedDyn | 81.4 | Not recorded | 68fa5da71e209131ce9dbecb | | FedLap-Cov | 81.3 | Not recorded | 68fa5da71e209131ce9dbecb | | FedLap | 79.4 | Not recorded | 68fa5da71e209131ce9dbecb | | FedAvg/FedProx | 78.7 | Not recorded | 68fa5da71e209131ce9dbecb | | IVON-ADMM@mg | 78.7 | Not recorded | 68fa5da71e209131ce9dbecb | | IVON-ADMM | 78.7 | Not recorded | 68fa5da71e209131ce9dbecb | | FedLap-Cov | 76.9 | Not recorded | 68fa5da71e209131ce9dbecb | | FedDyn | 75.7 | Not recorded | 68fa5da71e209131ce9dbecb | | FedAvg/FedProx | 73.9 | Not recorded | 68fa5da71e209131ce9dbecb | | FedLap | 73.9 | Not recorded | 68fa5da71e209131ce9dbecb | ### FedLap-Cov Test Accuracy: 83. Result ID: 69a872946dbb7075b950704c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"50","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### IVON-ADMM Test Accuracy: 83. Result ID: 69a872946dbb7075b9507052. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"50","Posterior Averaging":"Full posterior","Backbone":"MLP"}. This record does not assert independent reproduction. ### IVON-ADMM@mg Test Accuracy: 82.9. Result ID: 69a872946dbb7075b950704f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"50","Posterior Averaging":"Mean weight only","Backbone":"MLP"}. This record does not assert independent reproduction. ### FedLap Test Accuracy: 82.4. Result ID: 69a872946dbb7075b9507049. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"50","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### IVON-ADMM Test Accuracy: 82.3. Result ID: 69a872946dbb7075b9507051. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"25","Posterior Averaging":"Full posterior","Backbone":"MLP"}. This record does not assert independent reproduction. ### FedDyn Test Accuracy: 82.2. Result ID: 69a872946dbb7075b9507046. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"50","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### IVON-ADMM@mg Test Accuracy: 82.2. Result ID: 69a872946dbb7075b950704e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"25","Posterior Averaging":"Mean weight only","Backbone":"MLP"}. This record does not assert independent reproduction. ### FedAvg/FedProx Test Accuracy: 81.8. Result ID: 69a872946dbb7075b9507043. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"50","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### FedDyn Test Accuracy: 81.4. Result ID: 69a872946dbb7075b9507045. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"25","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### FedLap-Cov Test Accuracy: 81.3. Result ID: 69a872946dbb7075b950704b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"25","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### FedLap Test Accuracy: 79.4. Result ID: 69a872946dbb7075b9507048. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"25","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### FedAvg/FedProx Test Accuracy: 78.7. Result ID: 69a872946dbb7075b9507042. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"25","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### IVON-ADMM@mg Test Accuracy: 78.7. Result ID: 69a872946dbb7075b950704d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"10","Posterior Averaging":"Mean weight only","Backbone":"MLP"}. This record does not assert independent reproduction. ### IVON-ADMM Test Accuracy: 78.7. Result ID: 69a872946dbb7075b9507050. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"10","Posterior Averaging":"Full posterior","Backbone":"MLP"}. This record does not assert independent reproduction. ### FedLap-Cov Test Accuracy: 76.9. Result ID: 69a872946dbb7075b950704a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"10","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### FedDyn Test Accuracy: 75.7. Result ID: 69a872946dbb7075b9507044. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"10","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### FedAvg/FedProx Test Accuracy: 73.9. Result ID: 69a872946dbb7075b9507041. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"10","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. ### FedLap Test Accuracy: 73.9. Result ID: 69a872946dbb7075b9507047. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Communication Rounds":"10","Backbone":"MLP","Number of Clients":"100","Data Distribution":"Heterogeneous"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.