# Image Classification on EMNIST (Non-IID, alpha=0.8) Source: [Image Classification on EMNIST (Non-IID, alpha=0.8)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:18.520Z Evaluation of Image Classification performance on the EMNIST dataset configured for Non-IID data distribution using a Dirichlet alpha parameter of 0.8. 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) | EMNIST Non-IID (Dirichlet alpha = 0.8) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [CV](): Lower is better; unit: SCALAR. - [Max-Min Range](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FLEX-MoE | 86.91 | Not recorded | 69535c7253fdd5c36173d7f7 | | Greedy | 86.18 | Not recorded | 69535c7253fdd5c36173d7f7 | | Greedy | 85.06 | Not recorded | 69535c7253fdd5c36173d7f7 | | FLEX-MoE | 83.88 | Not recorded | 69535c7253fdd5c36173d7f7 | | Random | 83.26 | Not recorded | 69535c7253fdd5c36173d7f7 | ### FLEX-MoE Accuracy: 86.91. Result ID: 699936aa5698665ec49fff8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Indicator":"Loss-driven","Client count C":20,"Expert count E":8,"Expert selection range kc":"\[2, 6\]"}. This record does not assert independent reproduction. ### Greedy Accuracy: 86.18. Result ID: 699936aa5698665ec49fff8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Indicator":"Acc-driven","Client count C":20,"Expert count E":8,"Expert selection range kc":"\[2, 6\]"}. This record does not assert independent reproduction. ### Greedy Accuracy: 85.06. Result ID: 699936aa5698665ec49fff8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Indicator":"Loss-driven","Client count C":20,"Expert count E":8,"Expert selection range kc":"\[2, 6\]"}. This record does not assert independent reproduction. ### FLEX-MoE Accuracy: 83.88. Result ID: 699936aa5698665ec49fff8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Indicator":"Acc-driven","Client count C":20,"Expert count E":8,"Expert selection range kc":"\[2, 6\]"}. This record does not assert independent reproduction. ### Random Accuracy: 83.26. Result ID: 699936aa5698665ec49fff8b. [Reporting paper]() Recorded evaluation configuration: {"Indicator":"None","Client count C":20,"Expert count E":8,"Expert selection range kc":"\[2, 6\]"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.