FedScale
breaching
Our great sponsors
| FedScale | breaching | |
|---|---|---|
| 4 | 1 | |
| 365 | 241 | |
| 3.0% | - | |
| 7.9 | 0.0 | |
| 4 months ago | 8 days ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
FedScale
-
University of Michigan Researchers Open-Source ‘FedScale’: a Federated Learning (FL) Benchmarking Suite with Realistic Datasets and a Scalable Runtime to Enable Reproducible FL Research on Privacy-Preserving Machine Learning
Continue reading | Checkout the paper, github link
- We created the most comprehensive benchmark datasets for federated learning to date!
- The most comprehensive benchmark datasets for federated learning to date!
-
The most comprehensive benchmark datasets for federated learning to date
We created FedScale, which has a diverse set of challenging and realistic benchmark datasets to facilitate scalable, comprehensive, and reproducible federated learning (FL) research. FedScale datasets are large-scale, encompassing a diverse range of important FL tasks, such as image classification, object detection, word prediction, and speech recognition. Our evaluation platform provides flexible APIs to implement new FL algorithms and includes new execution backends with minimal developer efforts. Check it out, and feel free to join the FedScale community via Slack(https://join.slack.com/t/fedscale/shared_invite/zt-uzouv5wh-ON8ONCGIzwjXwMYDC2fiKw)!
Paper: https://arxiv.org/abs/2105.11367 and Github repo: https://github.com/symbioticlab/fedscale
Cheers!
breaching
-
[P] Here's our new framework for Privacy Attacks in Federated Learning
We recently uploaded our framework for privacy attacks in federated learning. You can find it here: https://github.com/JonasGeiping/breaching. We include a sizable number of known attacks for deep neural networks in vision and text domains and some new ones.
What are some alternatives?
flower - Flower: A Friendly Federated Learning Framework
FederatedScope - An easy-to-use federated learning platform
FATE - An Industrial Grade Federated Learning Framework
fedjax - FedJAX is a JAX-based open source library for Federated Learning simulations that emphasizes ease-of-use in research.
pytorch-lightning - The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate. [Moved to: https://github.com/PyTorchLightning/pytorch-lightning]
ORBIT-Dataset - The ORBIT dataset is a collection of videos of objects in clean and cluttered scenes recorded by people who are blind/low-vision on a mobile phone. The dataset is presented with a teachable object recognition benchmark task which aims to drive few-shot learning on challenging real-world data.
federated-xgboost - Federated gradient boosted decision tree learning
datasets - TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]