no code implementations • 16 May 2023 • Jed Mills, Jia Hu, Geyong Min
FedAvg can improve the communication-efficiency of training by performing more steps of Stochastic Gradient Descent (SGD) on clients in each round.
no code implementations • 3 Apr 2023 • Chi Zhang, Wenjie Ruan, Fu Wang, Peipei Xu, Geyong Min, Xiaowei Huang
Verification plays an essential role in the formal analysis of safety-critical systems.
no code implementations • 12 Sep 2021 • Jin Wang, Jia Hu, Jed Mills, Geyong Min, Ming Xia
Federated learning (FL) is a privacy-preserving distributed machine learning paradigm that enables collaborative training among geographically distributed and heterogeneous devices without gathering their data.
no code implementations • 20 Aug 2021 • Chenyuan Feng, Howard H. Yang, Deshun Hu, Zhiwei Zhao, Tony Q. S. Quek, Geyong Min
Finally, we provide experiments to evaluate the learning performance of HFL and our MACFL.
1 code implementation • 20 Aug 2021 • Jed Mills, Jia Hu, Geyong Min, Rui Jin, Siwei Zheng, Jin Wang
To address this challenge, we propose a novel, generalised approach for incorporating adaptive optimisation into FL with the Federated Global Biased Optimiser (FedGBO) algorithm.
1 code implementation • 16 Dec 2020 • Jin Wang, Jia Hu, Geyong Min, Qiang Ni, Tarek El-Ghazawi
To address these challenges, we propose a novel learning-driven method, which is user-centric and can make effective online migration decisions by utilizing incomplete system-level information.
1 code implementation • 5 Aug 2020 • Jin Wang, Jia Hu, Geyong Min, Albert Y. Zomaya, Nektarios Georgalas
Recently, many deep reinforcement learning (DRL) based methods have been proposed to learn offloading policies through interacting with the MEC environment that consists of UE, wireless channels, and MEC hosts.
1 code implementation • 17 Jul 2020 • Jed Mills, Jia Hu, Geyong Min
MTFL is compatible with popular iterative FL optimisation algorithms such as Federated Averaging (FedAvg), and we show empirically that a distributed form of Adam optimisation (FedAvg-Adam) benefits convergence speed even further when used as the optimisation strategy within MTFL.
1 code implementation • 1 Jul 2020 • Jed Mills, Jia Hu, Geyong Min
The rapidly expanding number of Internet of Things (IoT) devices is generating huge quantities of data, but public concern over data privacy means users are apprehensive to send data to a central server for machine learning (ML) purposes.
no code implementations • 1 Apr 2020 • Zheyi Chen, Jia Hu, Geyong Min, Albert Y. Zomaya, Tarek El-Ghazawi
Resource provisioning for cloud computing necessitates the adaptive and accurate prediction of cloud workloads.
no code implementations • 30 Jan 2020 • Joseph Billingsley, Ke Li, Wang Miao, Geyong Min, Nektarios Georgalas
The ever increasing demand for computing resources has led to the creation of hyperscale datacentres with tens of thousands of servers.
no code implementations • 5 Jan 2020 • Zijian Liu, Chunbo Luo, Shuai Li, Peng Ren, Geyong Min
This paper proposes fractional order graph neural networks (FGNNs), optimized by the approximation strategy to address the challenges of local optimum of classic and fractional graph neural networks which are specialised at aggregating information from the feature and adjacent matrices of connected nodes and their neighbours to solve learning tasks on non-Euclidean data such as graphs.
no code implementations • 30 Sep 2019 • Ke Li, Min-Hui Liao, Kalyanmoy Deb, Geyong Min, Xin Yao
The ultimate goal of multi-objective optimisation is to help a decision maker (DM) identify solution(s) of interest (SOI) achieving satisfactory trade-offs among multiple conflicting criteria.
no code implementations • 13 May 2019 • Tianxiao Zhao, Chunbo Luo, Geyong Min, Jianming Zhou, Dechun Guo, Wang Miao, Yang Mi
Then, we propose a DoA estimation algorithm and a steering vector adaptive receiving beam forming method.
no code implementations • 23 Jan 2019 • He Zhang, Xingrui Yu, Peng Ren, Chunbo Luo, Geyong Min
The novelty of the proposed framework focuses on incorporating deep adversarial learning with statistical learning and exploiting learning based data augmentation.
no code implementations • Thirty-Second AAAI Conference on Artificial Intelligence 2018 • Chengqiang Huang, Yulei Wu, Yuan Zuo, Ke Pei, Geyong Min
This abstract proposes a time series anomaly detector which 1) makes no assumption about the underlying mechanism of anomaly patterns, 2) refrains from the cumbersome work of threshold setting for good anomaly detection performance under specific scenarios, and 3) keeps evolving with the growth of anomaly detection experience.
no code implementations • 30 Sep 2016 • Xing Zhang, Zhenglei Yi, Zhi Yan, Geyong Min, Wenbo Wang, Sabita Maharjan, Yan Zhang
Mobile big data contains vast statistical features in various dimensions, including spatial, temporal, and the underlying social domain.