Flower Baselines Documentation
==============================

Welcome to Flower Baselines' documentation. `Flower <https://flower.ai>`_ is a friendly federated learning framework.


Join the Flower Community
-------------------------

The Flower Community is growing quickly - we're a friendly group of researchers, engineers, students, professionals, academics, and other enthusiasts.

.. button-link:: https://flower.ai/join-slack
    :color: primary
    :shadow:

    Join us on Slack


Flower Baselines
----------------

Flower Baselines are a collection of organised directories used to reproduce results from well-known publications or benchmarks. You can check which baselines already exist and/or contribute your own baseline.


.. list-table:: 
   :widths: 15 15 50
   :header-rows: 1
  
   * - Method
     - Dataset
     - Tags
   
   * - `dasha <dasha.html>`_
     - cifar10, mushrooms, libsvm
     - compression, heterogeneous setting, variance reduction, image classification
    

   * - `depthfl <depthfl.html>`_
     - CIFAR-100
     - image classification, system heterogeneity, cross-device, knowledge distillation
    

   * - `fedavgm <fedavgm.html>`_
     - CIFAR-10, Fashion-MNIST
     - non-iid, image classification
    

   * - `fedbn <fedbn.html>`_
     - MNIST, MNIST-M, SVHN, USPS, SynthDigits
     - data heterogeneity, feature shift, cross-silo
    

   * - `fedmeta <fedmeta.html>`_
     - FEMNIST, SHAKESPEARE
     - meta learning, maml, meta-sgd, personalization 
    

   * - `fedmlb <fedmlb.html>`_
     - CIFAR-100, Tiny-ImageNet 
     - data heterogeneity, knowledge distillation, image classification 
    

   * - `fednova <fednova.html>`_
     - CIFAR-10
     - normalized averaging, heterogeneous optimization, image classification
    

   * - `fedpara <fedpara.html>`_
     - CIFAR-10, CIFAR-100, MNIST
     - image classification, personalization, low-rank training, tensor decomposition
    

   * - `fedper <fedper.html>`_
     - CIFAR-10, FLICKR-AES 
     - system heterogeneity, image classification, personalization, horizontal data partition 
    

   * - `fedpft <fedpft.html>`_
     - CIFAR-100, Caltech101
     - foundation-models, pre-trained, one-shot, one-round
    

   * - `fedprox <fedprox.html>`_
     - MNIST
     - image classification, cross-device, stragglers
    

   * - `fedrep <fedrep.html>`_
     - CIFAR-10, CIFAR-100
     - image classification, label heterogeneity, personalized federated learning
    

   * - `fedstar <fedstar.html>`_
     - Ambient Context, Speech Commands
     - Audio Classification, Semi Supervised learning
    

   * - `fedvssl <fedvssl.html>`_
     - UCF-101, Kinectics-400
     - action recognition, cross-device, ssl, video, videossl
    

   * - `fedwav2vec2 <fedwav2vec2.html>`_
     - TED-LIUM 3
     - speech, asr, cross-device
    

   * - `fjord <fjord.html>`_
     - "CIFAR-10"
     - "Federated Learning", "Heterogeneity", "Efficient DNNs", "Distributed Systems"
    

   * - `flanders <flanders.html>`_
     - MNIST, FashionMNIST
     - robustness, model poisoning, anomaly detection, autoregressive model, regression, classification
    

   * - `heterofl <heterofl.html>`_
     - MNIST, CIFAR-10
     - system heterogeneity, image classification
    

   * - `hfedxgboost <hfedxgboost.html>`_
     - a9a, cod-rna, ijcnn1, space_ga, cpusmall, YearPredictionMSD 
     - cross-silo, tree-based, XGBoost, Classification, Regression, Tabular 
    

   * - `moon <moon.html>`_
     - CIFAR-10, CIFAR-100
     - data heterogeneity, image classification, cross-silo, constrastive-learning
    

   * - `niid_bench <niid_bench.html>`_
     - CIFAR-10, MNIST, Fashion-MNIST
     - data heterogeneity, image classification, benchmark
    

   * - `tamuna <tamuna.html>`_
     - MNIST
     - local training, communication compression, partial participation, variance reduction
    
.. BASELINES_TABLE_ENTRY                                            
  


Tutorials
~~~~~~~~~

A learning-oriented series of tutorials, the best place to start.

.. note::
  Coming soon


How-to guides
~~~~~~~~~~~~~

Problem-oriented how-to guides show step-by-step how to achieve a specific goal.

.. toctree::
  :maxdepth: 1
  :caption: How-to Guides

  how-to-use-baselines
  how-to-contribute-baselines


Explanations
~~~~~~~~~~~~

Understanding-oriented concept guides explain and discuss key topics and underlying ideas behind Flower and collaborative AI.

.. note::
  Coming soon

References
~~~~~~~~~~

Information-oriented API reference and other reference material.

.. toctree::
  :maxdepth: 1
  :caption: References

  dasha
  depthfl
  fedavgm
  fedbn
  fedmeta
  fedmlb
  fednova
  fedpara
  fedper
  fedpft
  fedprox
  fedrep
  fedstar
  fedvssl
  fedwav2vec2
  fjord
  flanders
  heterofl
  hfedxgboost
  moon
  niid_bench
  tamuna