Zhengjie Yang

Dr. Zhengjie Yang

School of Computer Science, University of Sydney, Sydney, New South Wales, Australia
+1
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2017 in IEEE Communications Magazine
Verified
Journal Article
Closed access
WBWei Bao
Wei Bao
DYDong Yuan
Dong Yuan
Zhengjie YangZhengjie Yang
Zhengjie Yang
SWShen Wang
Shen Wang
WLWei Li
Wei Li
Albert ZomayaAlbert Zomaya
Albert Zomaya
Equipped with easy-to-access micro computation access points, the fog computing architecture provides low-latency and ubiquitously available computation offloading services to many simple and cheap Internet of Things devices with limited computing and energy resources. One obstacle, however, is how to seamlessly hand over mobile IoT devices among different computation access points when computation offloading is in action so that the offloading service is not interrupted - especially for time-sensitive applications. In this article, we propose Follow Me Fog (FMF), a framework supporting a new seamless handover timing scheme among different computation access points. Intrinsically, FMF supports a job pre-migration mechanism, which pre-migrates computation jobs when the handover is expected to happen. Such expectations can be indicated by constantly monitoring received signal strengths. Then we present the design and a prototype implementation of FMF. Our evaluation results demonstrate that FMF can achieve a substantial latency reduction (36.5 percent in our experiment). In conclusion, the FMF design clears a core obstacle, allowing fog computing to provide interruption-resistant services to mobile IoT devices.

14 September 2022 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
Zhengjie YangZhengjie Yang
Zhengjie Yang
WBWei Bao
Wei Bao
DYDong Yuan
Dong Yuan
NTNguyen H. Tran
Nguyen H. Tran
Albert ZomayaAlbert Zomaya
Albert Zomaya
Federated learning (FL) is a fast-developing technique that allows multiple workers to train a global model based on a distributed dataset. Conventional FL (FedAvg) employs gradient descent algorithm, which may not be efficient enough. Momentum is able to improve the situation by adding an additional momentum step to accelerate the convergence and has demonstrated its benefits in both centralized and FL environments. It is well-known that Nesterov Accelerated Gradient (NAG) is a more advantageous form of momentum, but it is not clear how to quantify the benefits of NAG in FL so far. This motives us to propose FedNAG, which employs NAG in each worker as well as NAG momentum and model aggregation in the aggregator. We provide a detailed convergence analysis of FedNAG and compare it with FedAvg. Extensive experiments based on real-world datasets and trace-driven simulation are conducted, demonstrating that FedNAG increases the learning accuracy by 3–24% and decreases the total training time by 11–70% compared with the benchmarks under a wide range of settings.

12 July 2023 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Open access
Zhengjie YangZhengjie Yang
Zhengjie Yang
SFSen Fu
Sen Fu
WBWei Bao
Wei Bao
DYDong Yuan
Dong Yuan
Albert ZomayaAlbert Zomaya
Albert Zomaya
In this article, we propose Hierarchical Federated Learning with Momentum Acceleration (HierMo), a three-tier worker-edge-cloud federated learning algorithm that applies momentum for training acceleration. Momentum is calculated and aggregated in the three tiers. We provide convergence analysis for HierMo, showing a convergence rate of $\mathcal {O}(\frac{1}{T})$ . In the analysis, we develop a new approach to characterize model aggregation, momentum aggregation, and their interactions. Based on this result, we prove that HierMo achieves a tighter convergence upper bound compared with HierFAVG without momentum. We also propose HierOPT, which optimizes the aggregation periods (worker-edge and edge-cloud aggregation periods) to minimize the loss given a limited training time. By conducting the experiment, we verify that HierMo outperforms existing mainstream benchmarks under a wide range of settings. In addition, HierOPT can achieve a near-optimal performance when we test HierMo under different aggregation periods.

1 July 2022 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
Zhengjie YangZhengjie Yang
Zhengjie Yang
SFSen Fu
Sen Fu
WBWei Bao
Wei Bao
DYDong Yuan
Dong Yuan
Albert ZomayaAlbert Zomaya
Albert Zomaya
In this paper, we propose and analyze FastSlowMo, a combined Nesterov accelerated gradient (NAG) style worker momentum and aggregator momentum algorithm for Federated Learning (FL). Existing NAG momentum-based FL algorithms depend on either worker momentum only or aggregator momentum only, which may be inefficient due to infrequent usage of momentum, data heterogeneity, and out-of-date momentum. FastSlowMo combines the advantages of worker momentum and aggregator momentum to address these issues. We then provide mathematical proof for the convergence of FastSlowMo. Finally, extensive experiments based on real-world datasets and trace-driven simulation are conducted, verifying that FastSlowMo decreases the total training time by 3–61%, and outperforms existing mainstream benchmarks under a wide range of settings.

25 October 2018
Verified
Conference Paper
Open access
WBWei Bao
Wei Bao
DYDong Yuan
Dong Yuan
Zhengjie YangZhengjie Yang
Zhengjie Yang
SWShen Wang
Shen Wang
BZBing Zhou
Bing Zhou
Albert ZomayaAlbert Zomaya
Albert Zomaya

19 December 2024 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
XSXinyi Sheng
Xinyi Sheng
Zhengjie YangZhengjie Yang
Zhengjie Yang
WBWei Bao
Wei Bao
Algorithmic fairness, emphasizing that machine learning algorithms should not discriminate against specific demographic groups, has recently gained increasing attention in the context of federated learning. Existing algorithmic fairness algorithms in federated learning primarily focus on mitigating inherent biases within the training data or biases introduced by non-IID data distributions. However, these methods heavily rely on the assumption of trust and cooperation among participants in federated learning, leaving a notable gap in exploring the robustness of algorithmic fairness under adversarial environments. Therefore, our study advocates the exploration of the robustness of algorithmic fairness in federated learning. We first introduce four types of fairness attacks targeting the fairness of federated learning models. Then, we propose FairGuard, an innovative defense framework designed to counter these attacks. FairGuard employs a novel dual-inference algorithm that effectively identifies malicious clients during the global aggregation phase of federated learning. Our comprehensive experiments demonstrate that the introduced fairness attacks significantly compromise the global model's fairness and cannot be effectively mitigated by existing defense mechanisms, while FairGuard exhibits remarkable effectiveness in defending against these fairness attacks.