Federated Learning over a Wireless Network: Distributed User Selection through Random Access

no code implementations • 7 Jul 2023 • Chen Sun, Shiyao Ma, Ce Zheng, Songtao Wu, Tao Cui, Lingjuan Lyu

This study proposes a network intrinsic approach of distributed user selection that leverages the radio resource competition mechanism in random access.

Fairness Federated Learning

Theoretical understanding of adversarial reinforcement learning via mean-field optimal control

no code implementations • 29 Sep 2021 • ZiMing Wang, Fengxiang He, Tao Cui, DaCheng Tao

A new mean-field Pontryagin's maximum principle is proposed for reinforcement learning with implicit terminal constraints.

Generalization Bounds reinforcement-learning +1

Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation

no code implementations • 26 Oct 2020 • Wei Wang, Yimeng Chai, Tao Cui, Chuang Wang, Baohua Zhang, Yue Li, Yi An

In recent studies, Generative Adversarial Network (GAN) is one of the popular schemes to augment the image dataset.

Data Augmentation Generative Adversarial Network

Study of Constrained Network Structures for WGANs on Numeric Data Generation

no code implementations • 5 Nov 2019 • Wei Wang, Chuang Wang, Tao Cui, Yue Li

Especially, Isomorphic WGAN is the best in 15/20 experiments.