UFed-GAN: A Secure Federated Learning Framework with Constrained Computation and Unlabeled Data
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Federated unsupervised representation learningFrontiers of Information Technology & Electronic Engineering, 2023
- PerFED-GAN: Personalized Federated Learning via Generative Adversarial NetworksIEEE Internet of Things Journal, 2022
- Computation‐constrained spectrum sensing in IoT‐based scenariosIET Communications, 2020
- Learning from positive and unlabeled data: a surveyMachine Learning, 2020
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004