paper-with-me

홈 › Papers

Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets

2021-03-17 · Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal, Shlomo Dubnov

Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive training data. In this paper, we experimentally show that FedGAN generates biased data points under non-independent-and-identically-distributed (non-iid) settings. Also, we propose Bias-Free FedGAN, an approach to generate bias-free synthetic datasets using FedGAN. Our approach generates metadata at the aggregator using the models received from clients and retrains the federated model to achieve bias-free results for image synthesis. Bias-Free FedGAN has the same communication cost as that of FedGAN. Experimental results on image datasets (MNIST and FashionMNIST) validate our claims.

📄 PDF Abstract BibTeX arXiv:2103.09876

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkImage Generation

Similar Papers 제목 키워드 기반

FedGAN: Federated Generative Adversarial Networks for Distributed Data

2020-06-12 · Mohammad Rasouli, Tao Sun, Ram Rajagopal

We propose Federated Generative Adversarial Network (FedGAN) for training a GAN across distributed sources of non-independent-and-identically-distributed data sources subject to communication and privacy constraints. Our…

Generative Adversarial NetworkTime SeriesTime Series Analysis

PS-FedGAN: An Efficient Federated Learning Framework Based on Partially Shared Generative Adversarial Networks For Data Privacy

2023-05-19 · Achintha Wijesinghe, Songyang Zhang, Zhi Ding

Federated Learning (FL) has emerged as an effective learning paradigm for distributed computation owing to its strong potential in capturing underlying data statistics while preserving data privacy. However, in cases of …

Federated Learning

Federated Learning for COVID-19 Detection with Generative Adversarial Networks in Edge Cloud Computing

2021-10-14 · Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne 외

COVID-19 has spread rapidly across the globe and become a deadly pandemic. Recently, many artificial intelligence-based approaches have been used for COVID-19 detection, but they often require public data sharing with cl…

Cloud ComputingFederated Learning

Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis

2022-10-19 · Ruinan Jin, Xiaoxiao Li

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research and augment medical datasets. Training generative adversarial neural networks…

Backdoor AttackData AugmentationFederated LearningGenerative Adversarial Network+2

Federated Adversarial Debiasing for Fair and Transferable Representations

2021-08-14 · the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining 2021 8 · Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Zhangyang Wang 외

Federated learning is a distributed learning framework that is communication efficient and provides protection over participating users' raw training data. One outstanding challenge of federate learning comes from the us…

Domain AdaptationFederated LearningUnsupervised Domain Adaptation