FedRep, MR-MTL, FedDG-GA, upgrading torch, flwr versions and more!

What's Changed

• Ditto FLamby implementation scripts. by @emersodb in #112
• Small fix for when sampling dataloaders produce an empty batch. by @emersodb in #114
• Fixing two small typos by @emersodb in #118
• Fixing an issue with Opacus modified models and optimizers. by @emersodb in #119
• Upgrading pycyclops to ^0.2.5 and removing exceptions on pip-audit by @lotif in #121
• Update torch, flwr and other requirements by @jewelltaylor in #120
• Displaying all the smoke tests metrics errors at once by @lotif in #122
• Updating the README to include Ditto by @emersodb in #123
• AG News Experiments and Basic Client Refactor by @yc7z in #124
• Adding an implementation for FedDG-GA by @lotif in #117
• Add MR-MTL Method by @sanaAyrml in #125
• Updating the start numpy client code. by @emersodb in #126
• Update tqdm (pip-audit found a vulnerability) by @amrit110 in #133
• Bump jinja2 from 3.1.3 to 3.1.4 by @dependabot in #140
• Bump werkzeug from 3.0.1 to 3.0.3 by @dependabot in #139
• Enable pre-commit ci and add default config by @amrit110 in #132
• Skip flake8 on pre-commit bot by @lotif in #141
• Implementing FedRep by @emersodb in #127
• Adding the ability to specify a checkpointing for models before aggregation. by @emersodb in #128
• Creating an Opacus specific Checkpointer by @emersodb in #129
• Forcing better model consistency for Server-side models with Opacus by @emersodb in #130
• Consolidate Weight Drift Losses by @emersodb in #131
• Add dependabot config to update github actions by @amrit110 in #142
• Bump actions/setup-python from 3 to 5 by @dependabot in #143
• Bump actions/checkout from 3 to 4 by @dependabot in #144
• Bump actions/cache from 2 to 4 by @dependabot in #145
• Bump pypa/gh-action-pypi-publish from 1.4.2 to 1.8.14 by @dependabot in #146

New Contributors

• @dependabot made their first contribution in #140

Full Changelog: v0.1.13...v0.1.15

Add Ditto, Aggregation utils, PICAI dataset utils

What's Changed

• Aggregation utils to main lib by @jewelltaylor in #110
• Picai example by @jewelltaylor in #101
• Implementing Ditto for paper experimentation by @emersodb in #111
• Increment release version by @jewelltaylor in #113

Full Changelog: v0.1.12...v0.1.13

Sparse Parameter Exchanger and Federated Autoencoders.

What's Changed

• Relax Floating Point Number Tolerance for PCA test by @yc7z in #106
• Add separate functions to save aggregated and old local models in Fenda and Moon by @sanaAyrml in #109
• Sparse Parameter Exchange by @yc7z in #103
• Federated ae by @fatemetkl in #82

Full Changelog: v0.1.11...v0.1.12

Smoke Tests, Fed PCA, Small Bug Fixes, README update

What's Changed

• Upgrading jinja2 to 3.1.3 to fix a security issue by @lotif in #96
• Add federated checkpointing by @sanaAyrml in #95
• Federated PCA by @yc7z in #89
• Add a reporter to save the metrics to a parseable file by @lotif in #92
• Smoke tests: Fix random seed on smoke tests and add asserts on results by @lotif in #97
• Ignoring one more pillow 9.5.0 vulnerability by @lotif in #99
• Initial Parameter Retrieval Code Duplication Reduction by @emersodb in #104
• README Update to include all of the new work! by @emersodb in #105
• Splitting Loss into EvaluationLoss and TrainLoss by @lotif in #100
• Update personalized approaches section header by @amrit110 in #107
• Fixing a small, but significant, bug with MOON. by @emersodb in #108

Full Changelog: v0.1.10...v0.1.11

Federated ensembling, Warmup Modules, Fixed seeds, and a lot of tests

What's Changed

• Add smoke tests for SCAFFOLD, APFL and others, Part 2 by @lotif in #79
• Smoke tests: display client logs on timeout by @lotif in #81
• Federated ensemble by @jewelltaylor in #77
• Fix random seed bug on initialized parameters by @lotif in #83
• Use poetry as the only source of dependency control by @lotif in #88
• Fix cyclops module import, adjust dependencies by @amrit110 in #90
• Add pip-audit to the CI checks by @lotif in #87
• Add warm up module by @sanaAyrml in #85
• Flamby experiments by @sanaAyrml in #86
• Flamby experiments by @sanaAyrml in #91
• Upgrading gitpython to 3.1.41 to fix a security issue by @lotif in #93
• Fixing a bug in the FedPer layers to exchange function by @emersodb in #94

Full Changelog: v0.1.9...v0.1.10

Bug fix associated with Basic Client

What's Changed

• Consolidate BasicClient and NumpyFlClient by @jewelltaylor in #74
• Set seed by @sanaAyrml in #75
• Build a first pass, basic smoke test associated with one of the examples by @lotif in #73
• Add smoke tests for SCAFFOLD, APFL and others, Part 1 by @lotif in #76
• bug fix in basic client by @yc7z in #80

New Contributors

• @lotif made their first contribution in #73

Full Changelog: v0.1.8...v0.1.9

FedBN, FedPer, MOON, PerFCL and bug fixes

What's Changed

• Updating README by @emersodb in #51
• Dbe/implement unweighted fedavg by @emersodb in #52
• Add functionality to support FedBN method by @emersodb in #53
• Adding in a citation line at the bottom. by @emersodb in #57
• Refactor of Losses default additional_losses to empty by @emersodb in #58
• Fixing a bug with the FedProx refactor in FLamby by @emersodb in #59
• Small fix to the find_best_hp.py script by @emersodb in #60
• Refactor setup client by @jewelltaylor in #54
• Machinery to support Federated Evaluation Only by @emersodb in #55
• Add Server-side Checkpointing to Server Base by @emersodb in #56
• Fix wandb by @jewelltaylor in #61
• Dbe/setting doc string format by @emersodb in #64
• Update apfl client by @jewelltaylor in #62
• Moon by @sanaAyrml in #66
• Add contrastive losses by @sanaAyrml in #67
• Feature alignment by @yc7z in #63
• Create Fixed Requirements File for FLamby, Update Dynamic Weight Exchanger and FedOpt Example by @emersodb in #68
• Metric refactor by @jewelltaylor in #69
• Checkpoint Ablation for Flamby by @emersodb in #71
• FedPer Implementation by @emersodb in #72

Full Changelog: v0.1.7...v0.1.8

FLamby, Partial Layer Exchange, Adaptive FedProx

What's Changed

• Exchanger refactor by @yc7z in #33
• First shot at fixing the server side parameter initialization issue. by @emersodb in #37
• Fixing the APFL implementation that occurs if there are frozen layers in a model by @emersodb in #38
• Adding Tests for the APFL and FENDA layer exchange flow. by @emersodb in #35
• Expanding the FLamby Experimental Setup by @emersodb in #34
• Expanding Basic Client by @emersodb in #36
• Fix FLamby FedAdam NaN Issue on Eval by @emersodb in #39
• Fixing scaffold on GPU by @emersodb in #42
• Refactoring the FLamby Code and Adding Fed Heart Disease by @emersodb in #40
• FLamby Visualization input generation scripts by @emersodb in #43
• First stab at adding in Open-source licensing by @emersodb in #44
• Partial exchange example by @yc7z in #45
• Adding final dataset (Fed IXI) to our experiments. by @emersodb in #47
• Dp scaffold by @jewelltaylor in #48
• Add train by epochs option to scaffold client by @jewelltaylor in #49
• Automate privacy accounting by @jewelltaylor in #50
• Fed prox adaptive mu by @sanaAyrml in #46

New Contributors

• @sanaAyrml made their first contribution in #46

Full Changelog: v0.1.6...v0.1.7

v0.1.6

What's Changed

• Dynamic layer exchange by @yc7z in #31
• Initial pass at FLamby Experimental Design by @emersodb in #30
• Other metrics by @fatemetkl in #32

New Contributors

• @fatemetkl made their first contribution in #32

Full Changelog: v0.1.5...v0.1.6

v0.1.5

What's Changed

• Example refactor by @yc7z in #28
• fixed bug with unpacking parameters and tests by @yc7z in #29

New Contributors

• @yc7z made their first contribution in #28

Full Changelog: v0.1.4...v0.1.5