Zobrazeno 1 - 10
of 5 272
pro vyhledávání: '"Qian, Yi"'
Semantic communication is of crucial importance for the next-generation wireless communication networks. The existing works have developed semantic communication frameworks based on deep learning. However, systems powered by deep learning are vulnera
Externí odkaz:
http://arxiv.org/abs/2404.13279
Federated learning (FL) has emerged as a distributed machine learning (ML) technique that can protect local data privacy for participating clients and improve system efficiency. Instead of sharing raw data, FL exchanges intermediate learning paramete
Externí odkaz:
http://arxiv.org/abs/2404.11035
Fine-tuning large language models (LLMs) with classic first-order optimizers entails prohibitive GPU memory due to the backpropagation process. Recent works have turned to zeroth-order optimizers for fine-tuning, which save substantial memory by usin
Externí odkaz:
http://arxiv.org/abs/2402.15173
Time series analysis is vital for numerous applications, and transformers have become increasingly prominent in this domain. Leading methods customize the transformer architecture from NLP and CV, utilizing a patching technique to convert continuous
Externí odkaz:
http://arxiv.org/abs/2402.05830
Transformer-based models have emerged as promising tools for time series forecasting. However, these model cannot make accurate prediction for long input time series. On the one hand, they failed to capture global dependencies within time series data
Externí odkaz:
http://arxiv.org/abs/2306.08325
Asynchronous federated learning aims to solve the straggler problem in heterogeneous environments, i.e., clients have small computational capacities that could cause aggregation delay. The principle of asynchronous federated learning is to allow the
Externí odkaz:
http://arxiv.org/abs/2306.01207
Autor:
Gong Jing, Qian Yi, Xu Ziyang, Chen Chaoqian, Jin Yijing, Zhang Junze, Li Zhipeng, Shi Xianming
Publikováno v:
Nanotechnology Reviews, Vol 13, Iss 1, Pp 142-61 (2024)
Given the pressing threat of global warming, it is imperative to promote CO2 emission reduction within the cement industry which is widely recognized as a major contributor to the overall carbon footprint. Limestone clay cement (LCC) emerges as a pro
Externí odkaz:
https://doaj.org/article/2844fb1adcc94b84b3ac2797f8b59aa4
Autor:
Wan-Yi Zhao, Zhong-Cheng Liu, Shi Shi, Jie-Lan Li, Ke-Wang Xu, Kang-You Huang, Zhi-Hui Chen, Ya-Rong Wang, Cui-Ying Huang, Yan Wang, Jing-Rui Chen, Xian-Ling Sun, Wen-Xing Liang, Wei Guo, Long-Yuan Wang, Kai-Kai Meng, Xu-Jie Li, Qian-Yi Yin, Ren-Chao Zhou, Zhao-Dong Wang, Hao Wu, Da-Fang Cui, Zhi-Yao Su, Guo-Rong Xin, Wei-Qiu Liu, Wen-Sheng Shu, Jian-Hua Jin, David E. Boufford, Qiang Fan, Lei Wang, Su-Fang Chen, Wen-Bo Liao
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)
Abstract Although it is well documented that mountains tend to exhibit high biodiversity, how geological processes affect the assemblage of montane floras is a matter of ongoing research. Here, we explore landform-specific differences among montane f
Externí odkaz:
https://doaj.org/article/46483f7a95fa42c0b7acf2519790e916
This paper presents an approximate wireless communication scheme for federated learning (FL) model aggregation in the uplink transmission. We consider a realistic channel that reveals bit errors during FL model exchange in wireless networks. Our stud
Externí odkaz:
http://arxiv.org/abs/2304.03359
Publikováno v:
Zhongguo quanke yixue, Vol 27, Iss 22, Pp 2797-2806 (2024)
In-depth interview is to understand the life experience and lifestyle of a certain social group through in-depth conversation with the respondents, explore the formation process of specific phenomena, and propose ideas and recommendations to solve pr
Externí odkaz:
https://doaj.org/article/d4092ad6c8b04f39a13fdc629e005e98