Zobrazeno 1 - 10
of 416
pro vyhledávání: '"Dai, Huaiyu"'
Autor:
Liu, Ji, Jia, Juncheng, Zhang, Hong, Yun, Yuhui, Wang, Leye, Zhou, Yang, Dai, Huaiyu, Dou, Dejing
Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three original
Externí odkaz:
http://arxiv.org/abs/2408.05678
Distributed training of deep neural networks faces three critical challenges: privacy preservation, communication efficiency, and robustness to fault and adversarial behaviors. Although significant research efforts have been devoted to addressing the
Externí odkaz:
http://arxiv.org/abs/2402.10816
Autor:
Liu, Ji, Che, Tianshi, Zhou, Yang, Jin, Ruoming, Dai, Huaiyu, Dou, Dejing, Valduriez, Patrick
Federated Learning (FL) has achieved significant achievements recently, enabling collaborative model training on distributed data over edge devices. Iterative gradient or model exchanges between devices and the centralized server in the standard FL p
Externí odkaz:
http://arxiv.org/abs/2312.10935
In today's digital landscape, journalists urgently require tools to verify the authenticity of facial images and videos depicting specific public figures before incorporating them into news stories. Existing deepfake detectors are not optimized for t
Externí odkaz:
http://arxiv.org/abs/2312.08034
Autor:
Liu, Ji, Jia, Juncheng, Che, Tianshi, Huo, Chao, Ren, Jiaxiang, Zhou, Yang, Dai, Huaiyu, Dou, Dejing
As a promising approach to deal with distributed data, Federated Learning (FL) achieves major advancements in recent years. FL enables collaborative model training by exploiting the raw data dispersed in multiple edge devices. However, the data is ge
Externí odkaz:
http://arxiv.org/abs/2312.05770
Autor:
Che, Tianshi, Liu, Ji, Zhou, Yang, Ren, Jiaxiang, Zhou, Jiwen, Sheng, Victor S., Dai, Huaiyu, Dou, Dejing
Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which limits the appl
Externí odkaz:
http://arxiv.org/abs/2310.15080
Decision-based black-box attacks often necessitate a large number of queries to craft an adversarial example. Moreover, decision-based attacks based on querying boundary points in the estimated normal vector direction often suffer from inefficiency a
Externí odkaz:
http://arxiv.org/abs/2308.03163
While a practical wireless network has many tiers where end users do not directly communicate with the central server, the users' devices have limited computation and battery powers, and the serving base station (BS) has a fixed bandwidth. Owing to t
Externí odkaz:
http://arxiv.org/abs/2308.01562
Autor:
Liwang, Minghui, Guo, Bingshuo, Ma, Zhanxi, Su, Yuhan, Jin, Jian, Hosseinalipour, Seyyedali, Wang, Xianbin, Dai, Huaiyu
To effectively process high volume of data across a fleet of dynamic and distributed vehicles, it is crucial to implement resource provisioning techniques that can provide reliable, cost-effective, and timely computing services. This article explores
Externí odkaz:
http://arxiv.org/abs/2307.15490
Vehicular clouds (VCs) are modern platforms for processing of computation-intensive tasks over vehicles. Such tasks are often represented as directed acyclic graphs (DAGs) consisting of interdependent vertices/subtasks and directed edges. In this pap
Externí odkaz:
http://arxiv.org/abs/2307.00777