349-exploiting-shared-representations-for-personalized-federated-learning

https://github.com/szu-advtech-2023/349-exploiting-shared-representations-for-personalized-federated-learning

Science Score: 18.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (10.2%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: SZU-AdvTech-2023
Language: Python
Default Branch: main
Size: 854 KB

Statistics

Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created over 2 years ago · Last pushed over 2 years ago

Metadata Files

Citation

https://github.com/SZU-AdvTech-2023/349-Exploiting-Shared-Representations-for-Personalized-Federated-Learning/blob/main/




## Dependencies

The code requires Python >= 3.6 and PyTorch >= 1.2.0. To install the other dependencies: `pip3 install -r requirements.txt`.

## Data

This code uses the CIFAR10, CIFAR100 datasets.

The CIFAR10, CIFAR100  datasets are downloaded automatically by the torchvision package. 



## Usage

FedRep is run using a command of the following form:

`python main_fedrep.py --alg fedrep --dataset [dataset] --num_users [num_users] --model [model] --model [model] --shard_per_user [shard_per_user] --frac [frac] --local_bs [local_bs] --lr [lr] --epochs [epochs] --local_ep [local_ep] --local_rep_ep [local_rep_ep] --gpu [gpu]`

Explanation of parameters:

- `alg` : algorithm to run, may be `fedrep`, `fedavg`, `prox` (FedProx), `fedper` (FedPer), or `lg` (LG-FedAvg)
- `dataset` : dataset, may be `cifar10`, `cifar100`, `femnist`, `mnist`, `sent140`
- `num_users` : number of users
- `model` : for the CIFAR datasets, we use `cnn`, for the MNIST datasets, we use `mlp`, and for `sent140`, we use `res`
- `num_classes` : total number of classes
- `shard_per_user` : number of classes per user (specific to CIFAR datasets and MNIST)
- `frac` : fraction of participating users in each round (for all experiments we use 0.1)
- `local_bs` : batch size used locally by each user
- `lr` : learning rate
- `epochs` : total number of communication rounds
- `local_ep` : total number of local epochs
- `local_rep_ep` : number of local epochs to execute for the representation (specific to FedRep)
- `gpu` : GPU ID

A full list of configuration parameters and their descriptions are given in `utils/options.py`.
For examples of running FedRep as well as the FL baselines we compare against, please see the executable files in `scripts/`, which recover the results from the paper.

Owner

Name: SZU-AdvTech-2023
Login: SZU-AdvTech-2023
Kind: organization

Repositories: 1
Profile: https://github.com/SZU-AdvTech-2023

Citation (citation.txt)

@article{REPO349,
    author = "Collins, Liam and Hassani, Hamed and Mokhtari, Aryan and Shakkottai, Sanjay",
    journal = "arXiv preprint arXiv:2102.07078",
    title = "{Exploiting Shared Representations for Personalized Federated Learning}",
    year = "2021"
}

GitHub Events

Total

Issues event: 1
Watch event: 1

Last Year

Issues event: 1
Watch event: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time

Total issues: 1
Total pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Total issue authors: 1
Total pull request authors: 0
Average comments per issue: 0.0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 1
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 1
Pull request authors: 0
Average comments per issue: 0.0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science