This repository contains research projects in federated learning from Webank AI group. It includes:
- Datasets. Preprocessing codes of datasets we used and developed for federated learning research.
- Publications. Implementation codes of our publications.
- Projects. Other projects in federated learning.
2020-11-06. The research directory is moved out from FATE project as an independent repository. Now you can get our latest research by staring this repo.
| Dataset | Description |
|---|---|
| Street Dataset | A real-world object detection dataset that annotates images captured by a set of street cameras based on object present in them, including 7 object categories. |
| Fed_ModelNet40 | It consists of images taken from various views of 3D models, and can be used for vertical federated learning research. |
| NUS WIDE | To simulate a vertical federated learning setting, the image features of samples is put on one party and the textual tags on another party. |
Backdoor attacks and defenses in feature-partitioned collaborative learning. (https://arxiv.org/abs/2007.03608)
Real-World Image Datasets for Federated Learning. (https://arxiv.org/abs/1910.11089)
Federated Transfer Reinforcement Learning for Autonomous Driving. (https://arxiv.org/abs/1910.06001)
FedMVT: Semi-supervised Vertical Federated Learning with MultiView Training. (https://arxiv.org/abs/2008.10838)
A Communication Efficient Collaborative Learning Framework for Distributed Features. (https://arxiv.org/abs/1912.11187)
Secure Federated Transfer Learning. (https://arxiv.org/abs/1812.03337)