UFed-GAN: A Secure Federated Learning Framework with Constrained Computation and Unlabeled Data
This work addresses federated learning for wireless communications applications where computational power is limited and data is unlabeled, offering an incremental improvement over existing methods.
The paper tackles the problem of federated learning in resource-constrained environments with unlabeled data by proposing UFed-GAN, an unsupervised federated generative adversarial network, which captures user-side data distributions without local classification training and demonstrates strong potential in preserving privacy.
To satisfy the broad applications and insatiable hunger for deploying low latency multimedia data classification and data privacy in a cloud-based setting, federated learning (FL) has emerged as an important learning paradigm. For the practical cases involving limited computational power and only unlabeled data in many wireless communications applications, this work investigates FL paradigm in a resource-constrained and label-missing environment. Specifically, we propose a novel framework of UFed-GAN: Unsupervised Federated Generative Adversarial Network, which can capture user-side data distribution without local classification training. We also analyze the convergence and privacy of the proposed UFed-GAN. Our experimental results demonstrate the strong potential of UFed-GAN in addressing limited computational resources and unlabeled data while preserving privacy.