FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning
- Zhen Wang, Weirui Kuang, Jingren Zhou
- Computer ScienceKnowledge Discovery and Data Mining
- 12 April 2022
This paper presents the implemented package FederatedScope-GNN (FS-G), which provides a unified view for modularizing and expressing FGL algorithms, and employs FS-G to serve the FGL application in real-world E-commerce scenarios, where the attained improvements indicate great potential business benefits.
FederatedScope: A Comprehensive and Flexible Federated Learning Platform via Message Passing
- Yuexiang Xie, Zhen Wang, Jingren Zhou
- Computer SciencearXiv.org
- 2022
A novel and comprehensive federated learning platform, named FederatedScope, which is based on a message-oriented framework, which frames an FL course into several rounds of message passing among participants, and allows developers to customize new types of exchanged messages and the corresponding handlers for various FL applications.
pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning
- Daoyuan Chen, Dawei Gao, Weirui Kuang, Yaliang Li, Bolin Ding
- Computer ScienceNeural Information Processing Systems
- 8 June 2022
The first comprehensive pFL benchmark, pFL-Bench, is proposed for facilitating rapid, reproducible, standardized and thorough pFL evaluation and highlights the benefits and potential of state-of-the-art pFL methods.
FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization
- Zhen Wang, Weirui Kuang, Ce Zhang, Bolin Ding, Yaliang Li
- Computer SciencearXiv.org
- 8 June 2022
This paper proposes and implements a benchmark suite FedHPO-B that incorporates comprehensive FL tasks, enables efficient function evaluations, and eases continuing extensions to facilitate the research of HPO in the FL setting.
Graph Neural Networks with Node-wise Architecture
- Zhen Wang, Zhewei Wei, Yaliang Li, Weirui Kuang, Bolin Ding
- Computer ScienceKnowledge Discovery and Data Mining
- 14 August 2022
A framework wherein the parametric controllers decide the GNN architecture for each node based on its local patterns, which significantly outperforms state-of-the-art methods on five of the ten real-world datasets, and confirms that node-wise architecture can help GNNs become versatile models.
A Benchmark for Federated Hetero-Task Learning
- Liuyi Yao, Dawei Gao, Yaliang Li
- Computer SciencearXiv.org
- 7 June 2022
This work generalizes the classic federated learning to federated hetero-task learning, which emphasizes the inconsistency across the participants in federatedLearning in terms of both data distribution and learning tasks, and presents B-FHTL, a federatedhetero- task learning benchmark consisting of simulation dataset, FL protocols and a unified evaluation mechanism.