activity
20182023
most citedCompacting Deep Neural Networks for Internet of Things: Methods and Applications

54 citations · 60 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2022★ 1 cited

HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse

Shenglai Zeng, Zonghang Li, Hongfang Yu +4

Federated Learning (FL), as a rapidly evolving privacy-preserving collaborative machine learning paradigm, is a promising approach to enable edge intelligence in the emerging Indus…

cs.LG2022

PerFED-GAN: Personalized Federated Learning via Generative Adversarial Networks

Xingjian Cao, Gang Sun, Hongfang Yu +1

Federated learning is gaining popularity as a distributed machine learning method that can be used to deploy AI-dependent IoT applications while protecting client data privacy and…

cs.LG2022

Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoT

Zonghang Li, Yihong He, Hongfang Yu +4

Nowadays, the industrial Internet of Things (IIoT) has played an integral role in Industry 4.0 and produced massive amounts of data for industrial intelligence. These data locate o…

cs.LG2022

Cross-Silo Heterogeneous Model Federated Multitask Learning

Xingjian Cao, Zonghang Li, Gang Sun +2

Federated learning (FL) is a machine learning technique that enables participants to collaboratively train high-quality models without exchanging their private data. Participants u…

cs.LG2022

Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training

Shenglai Zeng, Zonghang Li, Hongfang Yu +4

Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. In practical FL applications, local data from each data silo reflect local…

cs.LG2021★ 54 cited

Compacting Deep Neural Networks for Internet of Things: Methods and Applications

Ke Zhang, Hanbo Ying, Hong-Ning Dai +4

Deep Neural Networks (DNNs) have shown great success in completing complex tasks. However, DNNs inevitably bring high computational cost and storage consumption due to the complexi…