| --- |
| license: apache-2.0 |
| task_categories: |
| - image-classification |
| tags: |
| - federated-learning |
| - fedavg |
| - non-iid |
| - pytorch |
| --- |
| |
| # Federated Digits |
|
|
| Federated Digits simulates five data-siloed clients learning a shared 8x8 digit |
| classifier with Federated Averaging. Class samples are partitioned through a |
| low-concentration Dirichlet distribution, producing deliberately non-IID clients. |
|
|
| The project reports: |
|
|
| - per-client class distributions; |
| - global test accuracy after every communication round; |
| - client-update disagreement; |
| - a centralized training control using the same architecture. |
|
|
| No raw client examples are exchanged during federated rounds; only model parameters |
| are averaged. This is a local simulation, not a networked privacy guarantee. |
|
|
| ## Reproduce |
|
|
| ```powershell |
| uv run python projects/federated-digits/train.py |
| ``` |
|
|
| ## Verified results |
|
|
| - Model size: **2,410 parameters** |
| - Clients: **5**, with Dirichlet concentration `0.25` |
| - Communication rounds: **30**, with two local epochs per round |
| - Round-one global accuracy: **20.89%** |
| - Final global accuracy: **93.33%** |
| - Best global accuracy: **94.00%** |
| - Centralized control: **96.89%** |
| - Final federated-to-centralized gap: **-3.56 percentage points** |
|
|
| Mean client-update disagreement fell from 1.487 after the first round to 0.500 after |
| round 30. The artifact includes every round's accuracy, client loss, update |
| disagreement, and each client's class distribution. |
|
|
