Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Lingjuan Lyu"'
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-10 (2022)
Mainstream personalization methods rely on centralized Graph Neural Network learning on global graphs, which have considerable privacy risks due to the privacy-sensitive nature of user data. Here, the authors present a federated GNN framework for bot
Externí odkaz:
https://doaj.org/article/ea237068b27246548ff71dd0d8582ac8
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-8 (2022)
This work presents a communication-efficient federated learning method that saves a major fraction of communication cost. It reveals the advantage of reciprocal learning in machine knowledge transfer and the evolutional low-rank properties of deep mo
Externí odkaz:
https://doaj.org/article/d89508449f9f4c23abb84000b24c63d0
Publikováno v:
IEEE Access, Vol 8, Pp 190263-190276 (2020)
The interpolation of fine-grained air quality has significant prospects in the area of air quality monitoring. The solution to this problem can effectively monitor the air quality of the areas by sparse air quality monitoring stations, so as to reduc
Externí odkaz:
https://doaj.org/article/59f8122dd0d2406497d9838fcd0a2720
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. :1-13
3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D objects cannot change over time in the real-world. This unrealistic a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94e8a2aac37fb03a6a06866932415994
https://doi.org/10.1109/tnnls.2023.3247490
https://doi.org/10.1109/tnnls.2023.3247490
Publikováno v:
IEEE Transactions on Dependable and Secure Computing. :1-12
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e2a41127e8adc62b3ffb3245f9dd18cd
https://doi.org/10.1109/tdsc.2023.3276365
https://doi.org/10.1109/tdsc.2023.3276365
Autor:
Shiyao Ma, Jiangtian Nie, Jiawen Kang, Lingjuan Lyu, Ryan Wen Liu, Ruihui Zhao, Ziyao Liu, Dusit Niyato
Publikováno v:
IEEE Transactions on Industrial Informatics. 18:8977-8987
With the rapid development of cloud manufacturing, industrial production with edge computing as the core architecture has been greatly developed. However, edge devices often suffer from abnormalities and failures in industrial production. Therefore,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6ab56751dc29bccf59a465e261138cb
https://doi.org/10.1109/tii.2022.3167478
https://doi.org/10.1109/tii.2022.3167478
Publikováno v:
ACM Transactions on Intelligent Systems and Technology. 13:1-26
The fast growth of pre-trained models (PTMs) has brought natural language processing to a new era, which has become a dominant technique for various natural language processing (NLP) applications. Every user can download the weights of PTMs, then fin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d332f6416b6fd7eedb327bd7e6f4f30
https://doi.org/10.1145/3510033
https://doi.org/10.1145/3510033
Publikováno v:
IEEE Internet of Things Journal. 9:11365-11375
Federated machine learning which enables resource-constrained node devices (e.g., Internet of Things (IoT) devices, smartphones) to establish a knowledge-shared model while keeping the raw data local, could provide privacy preservation and economic b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c04f87075473bbc5fac4cf62ece5e043
https://doi.org/10.1109/jiot.2021.3128646
https://doi.org/10.1109/jiot.2021.3128646
Publikováno v:
ACM Transactions on Intelligent Systems and Technology. 13:1-19
Native ad is a popular type of online advertisement that has similar forms with the native content displayed on websites. Native ad click-through rate (CTR) prediction is useful for improving user experience and platform revenue. However, it is chall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4cfef8e37b99b258ec8c0d0a446ca388
https://doi.org/10.1145/3506715
https://doi.org/10.1145/3506715
Publikováno v:
IEEE Transactions on Industrial Informatics. 18:4059-4068
Due to resource constraints and working surroundings, many IIoT nodes are easily hacked and turn into zombies from which to launch attacks. It is challenging to detect such networked zombies. We combine federated learning (FL) and fog/edge computing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa3c557f4fe3e40cc03461836ba85513
https://doi.org/10.1109/tii.2021.3088938
https://doi.org/10.1109/tii.2021.3088938