Filters








3 Hits in 3.4 sec

FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis [article]

Guoyang Xie, Jinbao Wang, Yawen Huang, Yuexiang Li, Yefeng Zheng, Feng Zheng, Yaochu Jin
2022 arXiv   pre-print
In this paper, we propose a new benchmark for federated domain translation on unsupervised brain image synthesis (termed as FedMed-GAN) to bridge the gap between federated learning and medical GAN.  ...  There is a clear need to launch a federated learning and facilitate the integration of the dispersed data from different institutions.  ...  The pipeline of FedMed-GAN. Each client's generators and edge-net are shared with the server and take part in federated learning process.  ... 
arXiv:2201.08953v2 fatcat:kmd3vrcu7faavp3kx5v3n6o2uq

FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss [article]

Jinbao Wang, Guoyang Xie, Yawen Huang, Yefeng Zheng, Yaochu Jin, Feng Zheng
2022 arXiv   pre-print
In this paper, we propose a novel federated self-supervised learning (FedMed) for brain image synthesis.  ...  Experimental results verify the outstanding performance of our learning paradigm compared to other state-of-the-art approaches.  ...  [10] adopt a CNN-based method to speed up the registration procedure.  ... 
arXiv:2201.12589v3 fatcat:3ld6rzqadfatdkhzhpfavkbxbe

Semi-Decentralized Federated Edge Learning with Data and Device Heterogeneity [article]

Yuchang Sun and Jiawei Shao and Yuyi Mao and Jessie Hui Wang and Jun Zhang
2021 arXiv   pre-print
In this paper, we investigate a novel framework of FEEL, namely semi-decentralized federated edge learning (SD-FEEL), where multiple edge servers are employed to collectively coordinate a large number  ...  By exploiting the low-latency communication among edge servers for efficient model sharing, SD-FEEL can incorporate more training data, while enjoying much lower latency compared with conventional federated  ...  To speed up the training process, edge servers collaborate in training by sharing their models.  ... 
arXiv:2112.10313v1 fatcat:pbloayoztzci7fpugbtpzt75ti