activity
20192025
most citedFederated Learning with Differential Privacy: Algorithms and Performance Analysis

88 citations · 116 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2024

Trustworthy DNN Partition for Blockchain-enabled Digital Twin in Wireless IIoT Networks

Xiumei Deng, Jun Li, Long Shi +5

Digital twin (DT) has emerged as a promising solution to enhance manufacturing efficiency in industrial Internet of Things (IIoT) networks. To promote the efficiency and trustworth…

cs.LG2024

Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations

Yumeng Shao, Jun Li, Long Shi +6

Conventional synchronous federated learning (SFL) frameworks suffer from performance degradation in heterogeneous systems due to imbalanced local data size and diverse computing po…

cs.LG2024

Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization

Xiumei Deng, Jun Li, Kang Wei +6

Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However,…

cs.LG2023

Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction

Shuchi Wu, Chuan Ma, Kang Wei +4

This paper introduces RDA, a pioneering approach designed to address two primary deficiencies prevalent in previous endeavors aiming at stealing pre-trained encoders: (1) suboptima…

cs.LG20231 cited

Federated Meta-Learning for Few-Shot Fault Diagnosis with Representation Encoding

Jixuan Cui, Jun Li, Zhen Mei +5

Deep learning-based fault diagnosis (FD) approaches require a large amount of training data, which are difficult to obtain since they are located across different entities. Federat…

cs.LG2023

Analysis and Optimization of Wireless Federated Learning with Data Heterogeneity

Xuefeng Han, Jun Li, Wen Chen +4

With the rapid proliferation of smart mobile devices, federated learning (FL) has been widely considered for application in wireless networks for distributed model training. Howeve…