______ __               __                        __  
                            / ____// /              / /_   ___   ____   _____ / /_ 
                           / /_   / /     ______   / __ \ / _ \ / __ \ / ___// __ \
                          / __/  / /___  /_____/  / /_/ //  __// / / // /__ / / / /
                         /_/    /_____/          /_____/ \___//_/ /_/ \___//_/ /_/

This is a benchmark for evaluating well-known traditional, personalized and domain generalization federated learning methods. This benchmark straightforward and easy to extend.

Methods 🧬

Traditional FL Methods

• FedAvg -- Communication-Efficient Learning of Deep Networks from Decentralized Data (AISTATS'17)

• FedAvgM -- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification (ArXiv'19)

• FedProx -- Federated Optimization in Heterogeneous Networks (MLSys'20)

• SCAFFOLD -- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (ICML'20)

• MOON -- Model-Contrastive Federated Learning (CVPR'21)

• FedDyn -- Federated Learning Based on Dynamic Regularization (ICLR'21)

• FedLC -- Federated Learning with Label Distribution Skew via Logits Calibration (ICML'22)

• FedGen -- Data-Free Knowledge Distillation for Heterogeneous Federated Learning (ICML'21)

• CCVR -- No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data (NIPS'21)

• FedOpt -- Adaptive Federated Optimization (ICLR'21)

Personalized FL Methods

• pFedSim (My Work⭐) -- pFedSim: Similarity-Aware Model Aggregation Towards Personalized Federated Learning (ArXiv'23)

• Local-Only -- Local training only (without communication).

• FedMD -- FedMD: Heterogenous Federated Learning via Model Distillation (NIPS'19)

• APFL -- Adaptive Personalized Federated Learning (ArXiv'20)

• LG-FedAvg -- Think Locally, Act Globally: Federated Learning with Local and Global Representations (ArXiv'20)

• FedBN -- FedBN: Federated Learning On Non-IID Features Via Local Batch Normalization (ICLR'21)

• FedPer -- Federated Learning with Personalization Layers (AISTATS'20)

• FedRep -- Exploiting Shared Representations for Personalized Federated Learning (ICML'21)

• Per-FedAvg -- Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach (NIPS'20)

• pFedMe -- Personalized Federated Learning with Moreau Envelopes (NIPS'20)

• Ditto -- Ditto: Fair and Robust Federated Learning Through Personalization (ICML'21)

• pFedHN -- Personalized Federated Learning using Hypernetworks (ICML'21)

• pFedLA -- Layer-Wised Model Aggregation for Personalized Federated Learning (CVPR'22)

• CFL -- Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints (ArXiv'19)

• FedFomo -- Personalized Federated Learning with First Order Model Optimization (ICLR'21)

• FedBabu -- FedBabu: Towards Enhanced Representation for Federated Image Classification (ICLR'22)

• FedAP -- Personalized Federated Learning with Adaptive Batchnorm for Healthcare (IEEE'22)

• kNN-Per -- Personalized Federated Learning through Local Memorization (ICML'22)

• MetaFed -- MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcare (IJCAI'22)

FL Domain Generalization Methods

• FedSR -- FedSR: A Simple and Effective Domain Generalization Method for Federated Learning (NIPS'22)

• ADCOL -- Adversarial Collaborative Learning on Non-IID Features (ICML'23)

• FedIIR -- Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships (ICML'23)

Environment Preparation 🧩

PyPI 🐍

pip install -r requirements.txt

Conda 💻

conda env create -f environment.yml

Poetry 🎶

At China mainland

poetry install

Not at China mainland

sed -i "10,14d" pyproject.toml && poetry lock --no-update && poetry install

Docker 🐳

At China mainland

docker build -t fl-bench .

Not at China mainland

docker build \
-t fl-bench \
--build-arg IMAGE_SOURCE=karhou/ubuntu:basic \
--build-arg CHINA_MAINLAND=false \
.

Easy Run 🏃‍♂️

ALL classes of methods are inherited from FedAvgServer and FedAvgClient. If you wanna figure out the entire workflow and detail of variable settings, go check src/server/fedavg.py and src/client/fedavg.py.

# partition the CIFAR-10 according to Dir(0.1) for 100 clients
python generate_data.py -d cifar10 -a 0.1 -cn 100

# run FedAvg on CIFAR-10 with default settings.
# Use main.py like python main.py <method> [args ...]
# ❗ Method name should be identical to the `.py` file name in `src/server`.
python main.py fedavg -d cifar10

About methods of generating federated dastaset, go check data/README.md for full details.

Monitor 📈 (recommended 👍)

1. Run python -m visdom.server on terminal.
2. Run python main.py <method> --visible 1
3. Go check localhost:8097 on your browser.

Generic Arguments 🔧

📢 All generic arguments have their default value. Go check get_fedavg_argparser() in FL-bench/src/server/fedavg.py for full details of generic arguments.

You can also write your own .yaml config file. I offer you a template in config and recommend you to save your config files there also.

One example: python main.py fedavg -cfg config/template.yaml

About the default values and hyperparameters of advanced FL methods, go check corresponding FL-bench/src/server/<method>.py for full details.

Argument	Description
--dataset	The name of dataset that experiment run on.
--model	The model backbone experiment used.
--seed	Random seed for running experiment.
--join_ratio	Ratio for (client each round) / (client num in total).
--global_epoch	Global epoch, also called communication round.
--local_epoch	Local epoch for client local training.
--finetune_epoch	Epoch for clients fine-tunning their models before test.
--test_gap	Interval round of performing test on clients.
--eval_test	Non-zero value for performing evaluation on joined clients' testset before and after local training.
--eval_val	Non-zero value for performing evaluation on joined clients' valset before and after local training.
--eval_train	Non-zero value for performing evaluation on joined clients' trainset before and after local training.
-op, --optimizer	Client local optimizer, selected from [sgd, adam]
--local_lr	Learning rate for client local training.
--momentum	Momentum for client local opitimizer.
--weight_decay	Weight decay for client local optimizer.
--verbose_gap	Interval round of displaying clients training performance on terminal.
--batch_size	Data batch size for client local training.
--use_cuda	Non-zero value indicates that tensors are in gpu.
--visible	Non-zero value for using Visdom to monitor algorithm performance on localhost:8097.
--save_log	Non-zero value for saving algorithm running log in out/<method>.
--straggler_ratio	The ratio of stragglers (set in [0, 1]). Stragglers would not perform full-epoch local training as normal clients. Their local epoch would be randomly selected from range [--straggler_min_local_epoch, --local_epoch).
--straggler_min_local_epoch	The minimum value of local epoch for stragglers.
--external_model_params_file	The relative file path of external model parameters. Please confirm whether the shape of parameters compatible with the model by yourself. ⚠ This feature is enabled only when unique_model=False, which is pre-defined by each FL method.
--save_model	Non-zero value for saving output model(s) parameters in out/<method>.pt`.
--save_fig	Non-zero value for saving the accuracy curves showed on Visdom into a .jpeg file at out/<method>.
--save_metrics	Non-zero value for saving metrics stats into a .csv file at out/<method>.
--viz_win_name	Custom visdom window name (active when setting --visible as a non-zero value).
--config_file	Relative file path of custom config .yaml file.
--check_convergence	Non-zero value for checking convergence after training.

Supported Models 🚀

This benchmark supports bunch of models that common and integrated in Torchvision:

• ResNet family
• EfficientNet family
• DenseNet family
• MobileNet family
• LeNet5 ...

🤗 You can define your own custom model by filling the CustomModel class in src/utils/models.py and use it by specifying --model custom when running.

Supported Datasets 🎨

This benchmark only supports to solve image classification task for now.

Regular Image Datasets

• MNIST (1 x 28 x 28, 10 classes)

• CIFAR-10/100 (3 x 32 x 32, 10/100 classes)

• EMNIST (1 x 28 x 28, 62 classes)

• FashionMNIST (1 x 28 x 28, 10 classes)

• Syhthetic Dataset

• FEMNIST (1 x 28 x 28, 62 classes)

• CelebA (3 x 218 x 178, 2 classes)

• SVHN (3 x 32 x 32, 10 classes)

• USPS (1 x 16 x 16, 10 classes)

• Tiny-ImageNet-200 (3 x 64 x 64, 200 classes)

• CINIC-10 (3 x 32 x 32, 10 classes)

Domain Generalization Image Datasets

• DomainNet (3 x ? x ?, 345 classes)
  • Go check data/README.md for the full process guideline 🧾.

Medical Image Datasets

• COVID-19 (3 x 244 x 224, 4 classes)

• Organ-S/A/CMNIST (1 x 28 x 28, 11 classes)