# Federated Baseline Contributions! **URL:** \ **Category:** General\ **Created:** [January 19, 2025, 3:40pm UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602 "2025-01-19T15:40:04Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![williamlm](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/williamlm/32/162_2.png) [@williamlm](https://discuss.flower.ai/u/williamlm)\ **Post date:** [January 19, 2025, 3:40pm UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602/1 "2025-01-19T15:40:04Z")
Flower Labs is continuously looking to integrate baselines to our Flower framework. There’s always an opportunity to make a difference and contribute to open-source code by adding another cool baseline to the repository. Below you can find a list of baselines that can be implemented: - [FedDF - Ensemble Distillation for Robust Model Fusion in Federated Learning](https://proceedings.neurips.cc/paper/2020/hash/18df51b97ccd68128e994804f3eccc87-Abstract.html) - [FedNTD - Preservation of the Global Knowledge by Not-True Distillation in Federated Learning](https://papers.nips.cc/paper_files/paper/2022/hash/fadec8f2e65f181d777507d1df69b92f-Abstract-Conference.html) - [FedSAM - Improving Generalization in Federated Learning by Seeking Flat Minima](https://arxiv.org/abs/2203.11834) - [FedSMOO - Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape](https://arxiv.org/abs/2305.11584) - [q-FFL - Fair Resource Allocation in Federated Learning](https://openreview.net/forum?id=ByexElSYDr) - [FedMinMax - Minimax Demographic Group Fairness in Federated Learning](https://dl.acm.org/doi/10.1145/3531146.3533081) - [Power-of-Choice - Towards Understanding Biased Client Selection in Federated Learning](https://proceedings.mlr.press/v151/jee-cho22a.html) - [Oort - Efficient Federated Learning via Guided Participant Selection](https://www.usenix.org/conference/osdi21/presentation/lai) - [AdaS - Private Adaptive Optimization with Side information](https://proceedings.mlr.press/v162/li22x.html) - [Per-FedAvg - Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach](https://proceedings.neurips.cc/paper/2020/hash/24389bfe4fe2eba8bf9aa9203a44cdad-Abstract.html) - [FedPAC - Personalized Federated Learning with Feature Alignment and Classifier Collaboration](https://openreview.net/forum?id=SXZr8aDKia) - [pFedHN - Personalized Federated Learning using Hypernetworks](https://proceedings.mlr.press/v139/shamsian21a.html) - [FedFomo - Personalized Federated Learning with First Order Model Optimization](https://openreview.net/forum?id=ehJqJQk9cw) - [FedPM - Sparse Random Networks for Communication-Efficient Federated Learning](https://openreview.net/forum?id=k1FHgri5y3-) - [Scaffnew - ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!](https://proceedings.mlr.press/v162/mishchenko22b.html) - [EDEN - Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning](https://proceedings.mlr.press/v162/vargaftik22a) - [FedCVAE - Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity](https://openreview.net/forum?id=_hb4vM3jspB) - [FedDC - Federated Learning from Small Datasets](https://openreview.net/forum?id=hDDV1lsRV8) - [MoCoSFL - enabling cross-client collaborative self-supervised learning](https://openreview.net/forum?id=2QGJXyMNoPz) - [FedAUX - Leveraging Unlabeled Auxiliary Data in Federated Learning](https://ieeexplore.ieee.org/document/9632275) - [FedDM - Iterative Distribution Matching for Communication-Efficient Federated Learning](https://openaccess.thecvf.com/content/CVPR2023/html/Xiong_FedDM_Iterative_Distribution_Matching_for_Communication-Efficient_Federated_Learning_CVPR_2023_paper.html) - [ZeroFL - Efficient On-Device Training for Federated Learning with Local Sparsity](https://openreview.net/forum?id=2sDQwC_hmnM) - [FedSM - Closing the Generalization Gap of Cross-Silo Federated Medical Image Segmentation](https://openaccess.thecvf.com/content/CVPR2022/html/Xu_Closing_the_Generalization_Gap_of_Cross-Silo_Federated_Medical_Image_Segmentation_CVPR_2022_paper.html) - [FedMix - Approximation of Mixup under Mean Augmented Federated Learning](https://openreview.net/forum?id=Ogga20D2HO-) - [SSFL + KWS - Semi-Supervised Federated Learning for Keyword Spotting](https://arxiv.org/abs/2305.05110) - [EF21 - A New, Simpler, Theoretically Better, and Practically Faster Error Feedback](https://proceedings.neurips.cc/paper/2021/hash/231141b34c82aa95e48810a9d1b33a79-Abstract.html) - [FedHE - Heterogeneous Models and Communication-Efficient Federated Learning](https://arxiv.org/abs/2110.09910) - [Ditto - Fair and Robust Federated Learning Through Personalization](https://proceedings.mlr.press/v139/li21h.html) - [FedHarmony - Unlearning Scanner Bias with Distributed Data](https://conferences.miccai.org/2022/papers/216-Paper1639.html) - [FedSim - Similarity guided model aggregation for Federated Learning](https://doi.org/10.1016/j.neucom.2021.08.141) - [FedExP - Speeding Up Federated Averaging via Extrapolation](https://openreview.net/forum?id=IPrzNbddXV) - [SCAFFOLD - Stochastic Controlled Averaging for Federated Learning](https://proceedings.mlr.press/v119/karimireddy20a.html) - [FedGen - Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://arxiv.org/abs/2105.10056) - [FedBABU - Towards Enhanced Representation for Federated Image Classification](https://arxiv.org/abs/2106.06042) - [TablePuppet - A Generic Framework for Relational Federated Learning](https://arxiv.org/pdf/2403.15839v1) - [FedPG-BR - Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee](https://openreview.net/pdf?id=ospGnpuf6L) - [FedRS - Federated Learning with Restricted Softmax for Label Distribution Non-IID Data](https://dl.acm.org/doi/10.1145/3447548.3467254) - [FedDefender - FedDefender: Backdoor Attack Defense in Federated Learning](https://arxiv.org/abs/2307.08672) - [Ditto - Fair and Robust Federated Learning Through Personalization](https://arxiv.org/abs/2012.04221) Please express your interest for one of these baselines. Also, feel free to connect with us here and on Slack. ---
**Author:** ![gxenos](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/gxenos/32/171_2.png) [@gxenos](https://discuss.flower.ai/u/gxenos)\ **Post date:** [January 30, 2025, 3:29pm UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602/2 "2025-01-30T15:29:47Z")
Hi, I would like to work on FedSim. There is an issue already: [Add Flower Baseline: FedSim · Issue #2707 · adap/flower · GitHub](https://github.com/adap/flower/issues/2707) Should i create a new one? ---
**Author:** ![williamlm](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/williamlm/32/162_2.png) [@williamlm](https://discuss.flower.ai/u/williamlm)\ **Post date:** [January 30, 2025, 4:52pm UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602/3 "2025-01-30T16:52:33Z")
Hi @gxenos, Great that you’d like to work on FedSim. We will help you throughout the process of merging this to the main repository. Could you instead of opening an issue, create a Pull Request by following [this documentation](https://flower.ai/docs/baselines/how-to-contribute-baselines.html#add-a-new-flower-baseline)? Best regards Will ---
**Author:** ![williamlm](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/williamlm/32/162_2.png) [@williamlm](https://discuss.flower.ai/u/williamlm)\ **Post date:** [March 12, 2025, 5:14pm UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602/4 "2025-03-12T17:14:14Z")
Hi again, just checking in to see if we can help you open the pull request? @gxenos ---
**Author:** ![williamlm](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/williamlm/32/162_2.png) [@williamlm](https://discuss.flower.ai/u/williamlm)\ **Post date:** [April 24, 2025, 5:29pm UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602/5 "2025-04-24T17:29:34Z")
Hi @gxenos, just checking in here to see if you’re still interested in opening PR for this baseline? ---
**Author:** ![moeed1122](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/moeed1122/32/222_2.png) [@moeed1122](https://discuss.flower.ai/u/moeed1122)\ **Post date:** [May 5, 2025, 8:48am UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602/6 "2025-05-05T08:48:37Z")
I’m interested in implementing FedSAM Improving Generalization in Federated Learning by Seeking Flat Minima. Looking forward to contributing and connecting on Slack! ---
**Author:** ![javier](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/javier/32/116_2.png) [@javier](https://discuss.flower.ai/u/javier)\ **Post date:** [May 9, 2025, 3:16pm UTC](https://discuss.flower.ai/t/federated-baseline-contributions/602/7 "2025-05-09T15:16:47Z")
Hey @moeed1122 , It would be great to see `FedSAM` in the list of Flower Baselines indeed! You can follow the mini guide here to start creating a baseline: [Contribute Baselines - Flower Baselines 1.19.0](https://flower.ai/docs/baselines/how-to-contribute-baselines.html) — Let us know if you need of any support!