Search Results for author: Zhiguo Wan

Found 6 papers, 1 papers with code

High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers

no code implementations25 Jul 2023 Puning Zhao, Zhiguo Wan

In this paper, we design a new method that is suitable for high dimensional problems, under arbitrary number of Byzantine attackers.

Robust Nonparametric Regression under Poisoning Attack

no code implementations26 May 2023 Puning Zhao, Zhiguo Wan

The final estimate is nearly minimax optimal for arbitrary $q$, up to a $\ln N$ factor.

regression

Intelligent Computing: The Latest Advances, Challenges and Future

no code implementations21 Nov 2022 Shiqiang Zhu, Ting Yu, Tao Xu, Hongyang Chen, Schahram Dustdar, Sylvain Gigan, Deniz Gunduz, Ekram Hossain, Yaochu Jin, Feng Lin, Bo Liu, Zhiguo Wan, Ji Zhang, Zhifeng Zhao, Wentao Zhu, Zuoning Chen, Tariq Durrani, Huaimin Wang, Jiangxing Wu, Tongyi Zhang, Yunhe Pan

In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications.

Memory Regulation and Alignment toward Generalizer RGB-Infrared Person

1 code implementation18 Sep 2021 Feng Chen, Fei Wu, Qi Wu, Zhiguo Wan

The domain shift, coming from unneglectable modality gap and non-overlapped identity classes between training and test sets, is a major issue of RGB-Infrared person re-identification.

Attribute Metric Learning +1

Secure and Efficient Federated Learning Through Layering and Sharding Blockchain

no code implementations27 Apr 2021 Shuo Yuan, Bin Cao, Yao Sun, Zhiguo Wan, Mugen Peng

Introducing blockchain into Federated Learning (FL) to build a trusted edge computing environment for transmission and learning has attracted widespread attention as a new decentralized learning pattern.

Edge-computing Federated Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.