Zobrazeno 1 - 10
of 834
pro vyhledávání: '"Xu, Hongli"'
Mobile devices contribute more than half of the world's web traffic, providing massive and diverse data for powering various federated learning (FL) applications. In order to avoid the communication bottleneck on the parameter server (PS) and acceler
Externí odkaz:
http://arxiv.org/abs/2410.01256
Autor:
Bai, Kaixin, Zeng, Huajian, Zhang, Lei, Liu, Yiwen, Xu, Hongli, Chen, Zhaopeng, Zhang, Jianwei
Transparent object depth perception poses a challenge in everyday life and logistics, primarily due to the inability of standard 3D sensors to accurately capture depth on transparent or reflective surfaces. This limitation significantly affects depth
Externí odkaz:
http://arxiv.org/abs/2409.08926
Federated Learning (FL) enables distributed clients to collaboratively train models without exposing their private data. However, it is difficult to implement efficient FL due to limited resources. Most existing works compress the transmitted gradien
Externí odkaz:
http://arxiv.org/abs/2312.01617
Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems. To mitigate the computing/communication burden on resource-constrained workers and protect model privacy, spli
Externí odkaz:
http://arxiv.org/abs/2311.13348
Federated Learning (FL) has emerged to allow multiple clients to collaboratively train machine learning models on their private data at the network edge. However, training and deploying large-scale models on resource-constrained devices is challengin
Externí odkaz:
http://arxiv.org/abs/2307.15870
Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, dynamic network conditions and
Externí odkaz:
http://arxiv.org/abs/2212.09483
Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing (EC). Aided by EC, decentralized federated learning (DFL), which overcomes the single-point-of-failure problem in the parameter server (PS) based
Externí odkaz:
http://arxiv.org/abs/2212.02136
Publikováno v:
Foundations of Computing and Decision Sciences, Vol 49, Iss 1, Pp 95-118 (2024)
Automatic crack detection in construction facilities is a challenging yet crucial task. However, existing deep learning (DL)-based semantic segmentation methods for this field are based on fully supervised learning models and pixel-level manual annot
Externí odkaz:
https://doaj.org/article/62317abc42c14c2caa3cf16131515499
Autor:
Zhou, Jie, Tian, Mengjie, Zhang, Xiangchen, Xiong, Lingyi, Huang, Jinlong, Xu, Mengfan, Xu, Hongli, Yin, Zhucheng, Wu, Fengyang, Hu, Junjie, Liang, Xinjun, Wei, Shaozhong
Publikováno v:
In Journal of Affective Disorders 1 September 2024 360:97-107
Publikováno v:
In International Communications in Heat and Mass Transfer December 2024 159 Part B