[Feature Proposal] (New data partition strategy) Extended Dirichlet strategy

[liyipeng00]

Recently, I find one new data partition strategy called Extended Dirichlet strategy ~~~ ours :), which could be added in this repo.

It combines the two common partition strategies (i.e., Quantity-based class imbalance and Diribution-based class imbalance in Li et al. (2022)) to generate arbitrarily heterogeneous data. The difference is to add a step of allocating classes (labels) to determine the number of classes per client (denoted by $C$) before allocating samples via Dirichlet distribution (with concentrate parameter $\alpha$).

The implementation is in convergence. You can find more details in Convergence Analysis of Sequential Federated Learning on Heterogeneous Data.
[Figure:
Row 1: $C=2$ with $\alpha=0.1$, $\alpha=1.0$, $\alpha=10.0$;
Row 2: $C=5$ with $\alpha=0.1$, $\alpha=1.0$, $\alpha=10.0$;
Row 3: $C=10$ with $\alpha=0.1$, $\alpha=1.0$, $\alpha=10.0$; ]

Li, Q., Diao, Y., Chen, Q., & He, B. (2022, May). Federated learning on non-iid data silos: An experimental study. In 2022 IEEE 38th International Conference on Data Engineering (ICDE) (pp. 965-978). IEEE.

[AgentDS]

We will check your code. Thank you very much!

[liyipeng00]

Thanks. We are glad to hear from you. The code is ExDirPartition, and you can generate the map with the following command (changing the dataset location is required).

python partition.py -d mnist -n 10 --partition exdir -C 1 --alpha 1.0 

[AgentDS]

Interesting work!

[liyipeng00]

Thanks, =^_^=.