Tensor-Empowered LSTM for Communication-Efficient and Privacy-Enhanced Cognitive Federated Learning in Intelligent Transportation Systems
| العنوان: | Tensor-Empowered LSTM for Communication-Efficient and Privacy-Enhanced Cognitive Federated Learning in Intelligent Transportation Systems |
|---|---|
| المؤلفون: | Ruonan Zhao, Laurence T. Yang, Debin Liu, Wanli Lu, Chenlu Zhu, Yiheng Ruan |
| المصدر: | ACM Transactions on Multimedia Computing, Communications, and Applications. |
| بيانات النشر: | Association for Computing Machinery (ACM), 2023. |
| سنة النشر: | 2023 |
| مصطلحات موضوعية: | Computer Networks and Communications, Hardware and Architecture |
| الوصف: | Multimedia cognitive computing as a revolutionary emerging concept of Artificial Intelligence (AI) emulating the reasoning process like human brains could facilitate the evolution of Intelligent Transportation System (ITS) to be smarter, safer, and more efficient. Massive multimedia traffic big data is an important prerequisite for the success of cognitive computing in ITS. However, traditional data-centralized AI approaches often face the problems of data islands and data famine due to concerns about data privacy and security. To this end, we propose the concept of Cognitive Federated Learning (CFL) leveraging federated learning as the learning paradigm for cognitive computing, which solves the above concerns by sharing updated models rather than raw data. Nevertheless, the exchange of numerous model parameters not only generates significant communication overhead but also suffers from the risk of privacy leakage due to inference attacks. This paper aims to design a novel lightweight and privacy-enhanced CFL architecture to facilitate the development of ITS. Firstly, a privacy-enhanced model protection scheme with homomorphic encryption as the underlying technology is proposed to simultaneously defend against the inference attacks launched by external malicious attackers, honest-but-curious cognitive platform, and internal participants. Furthermore, a novel tensor ring-block decomposition and its corresponding deep computation model converting the weight tensor into a set of matrices and 3rd-order core tensors are proposed, which could reduce the communication overhead and storage requirements without compromising model performance. Experimental results on real-world datasets show that the proposed approach could perform well. |
| تدمد: | 1551-6865 1551-6857 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::8ffcc526cbe724e2d8f8f4b30bb4de4b https://doi.org/10.1145/3575661 |
| رقم الأكسشن: | edsair.doi...........8ffcc526cbe724e2d8f8f4b30bb4de4b |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 15516865 15516857 |
|---|