Zobrazeno 1 - 10
of 29 712
pro vyhledávání: '"Howard, H"'
Autor:
Li, Jiaxing, Chen, Zihan, Chong, Kai Fong Ernest, Das, Bikramjit, Quek, Tony Q. S., Yang, Howard H.
Leveraging over-the-air computations for model aggregation is an effective approach to cope with the communication bottleneck in federated edge learning. By exploiting the superposition properties of multi-access channels, this approach facilitates a
Externí odkaz:
http://arxiv.org/abs/2409.15100
Autor:
Chen, Jiao, He, Jiayi, Chen, Fangfang, Lv, Zuohong, Tang, Jianhua, Li, Weihua, Liu, Zuozhu, Yang, Howard H., Han, Guangjie
Currently, most applications in the Industrial Internet of Things (IIoT) still rely on CNN-based neural networks. Although Transformer-based large models (LMs), including language, vision, and multimodal models, have demonstrated impressive capabilit
Externí odkaz:
http://arxiv.org/abs/2409.01207
Image semantic communication (ISC) has garnered significant attention for its potential to achieve high efficiency in visual content transmission. However, existing ISC systems based on joint source-channel coding face challenges in interpretability,
Externí odkaz:
http://arxiv.org/abs/2408.03806
Autor:
Chen, Zhengchuan, Lang, Kang, Pappas, Nikolaos, Yang, Howard H., Wang, Min, Tian, Zhong, Quek, Tony Q. S.
Timely status updating is the premise of emerging interaction-based applications in the Internet of Things (IoT). Using redundant devices to update the status of interest is a promising method to improve the timeliness of information. However, parall
Externí odkaz:
http://arxiv.org/abs/2405.16965
In this paper, we introduce a novel mathematical framework for assessing the performance of joint communication and sensing (JCAS) in wireless networks, employing stochastic geometry as an analytical tool. We focus on deriving the meta distribution o
Externí odkaz:
http://arxiv.org/abs/2404.01672
Autor:
Wang, Chenhao, Chen, Zihan, Pappas, Nikolaos, Yang, Howard H., Quek, Tony Q. S., Poor, H. Vincent
We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. This approach capitalizes on the inherent superposition property of wireless channels, facilitating fast
Externí odkaz:
http://arxiv.org/abs/2403.06528
Autor:
Qian, Howard H., Lu, Yangxiao, Ren, Kejia, Wang, Gaotian, Khargonkar, Ninad, Xiang, Yu, Hang, Kaiyu
In order to successfully perform manipulation tasks in new environments, such as grasping, robots must be proficient in segmenting unseen objects from the background and/or other objects. Previous works perform unseen object instance segmentation (UO
Externí odkaz:
http://arxiv.org/abs/2403.01731
We leverage the Multiplicative Weight Update (MWU) method to develop a decentralized algorithm that significantly improves the performance of dynamic time division duplexing (D-TDD) in small cell networks. The proposed algorithm adaptively adjusts th
Externí odkaz:
http://arxiv.org/abs/2402.05641
Federated Learning (FL) has emerged as a privacy-preserving machine learning paradigm facilitating collaborative training across multiple clients without sharing local data. Despite advancements in edge device capabilities, communication bottlenecks
Externí odkaz:
http://arxiv.org/abs/2402.05407
Personalized federated learning (PFL) has been widely investigated to address the challenge of data heterogeneity, especially when a single generic model is inadequate in satisfying the diverse performance requirements of local clients simultaneously
Externí odkaz:
http://arxiv.org/abs/2401.17124