Fangyuan Zhao

Fangyuan Zhao

Auto-generated profile, based on publicly available information

Fangyuan Zhao

National Engineering Laboratory for Big Data Analytics (NEL-BDA), Xian Jiaotong University, Xian, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
19 October 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
FZFangyuan Zhao
Fangyuan Zhao
Xuebin RenXuebin Ren
Xuebin Ren
SYShusen Yang
Shusen Yang
QHQing Han
Qing Han
PZPeng Zhao
Peng Zhao
XYXinyu Yang
Xinyu Yang
Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for hidden semantic discovery of text data and serves as a fundamental tool for text analysis in various applications. However, the LDA model as well as the training process of LDA may expose the text information in the training data, thus bringing significant privacy concerns. To address the privacy issue in LDA, we systematically investigate the privacy protection of the main-stream LDA training algorithm based on Collapsed Gibbs Sampling (CGS) and propose several differentially private LDA algorithms for typical training scenarios. In particular, we present the first theoretical analysis on the inherent differential privacy guarantee of CGS based LDA training and further propose a centralized privacy-preserving algorithm (HDP-LDA) that can prevent data inference from the intermediate statistics in the CGS training. Also, we propose a locally private LDA training algorithm (LP-LDA) on crowdsourced data to provide local differential privacy for individual data contributors. Furthermore, we extend LP-LDA to an online version as OLP-LDA to achieve LDA training on locally private mini-batches in a streaming setting. Extensive analysis and experiment results validate both the effectiveness and efficiency of our proposed privacy-preserving LDA training algorithms.

30 October 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YLYanan Li
Yanan Li
Xuebin RenXuebin Ren
Xuebin Ren
FZFangyuan Zhao
Fangyuan Zhao
SYShusen Yang
Shusen Yang
Due to powerful data representation ability, deep learning has dramatically improved the state-of-the-art in many practical applications. However, the utility highly depends on fine-tuning of hyper-parameters, including learning rate, batch size, and network initialization. Although many first-order adaptive methods (e.g., Adam, Adagrad) have been proposed to adjust learning rate based on gradients, they are susceptible to the initial learning rate and network architecture. Therefore, the main challenge of using deep learning in practice is how to reduce the cost of tuning hyper-parameters. To address this, we propose a heuristic zeroth-order learning rate method, Adacomp, which adaptively adjusts the learning rate based only on values of the loss function. The main idea is that Adacomp penalizes large learning rates to ensure the convergence and compensates small learning rates to accelerate the training process. Therefore, Adacomp is robust to the initial learning rate. Extensive experiments, including comparison to six typically adaptive methods (Momentum, Adagrad, RMSprop, Adadelta, Adam, and Adamax) on several benchmark datasets for image classification tasks (MNIST, KMNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100), were conducted. Experimental results show that Adacomp is not only robust to the initial learning rate but also to the network architecture, network initialization, and batch size.

28 December 2022 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
LWLuhui Wang
Luhui Wang
Xuebin RenXuebin Ren
Xuebin Ren
CZCong Zhao
Cong Zhao
FZFangyuan Zhao
Fangyuan Zhao
SYShusen Yang
Shusen Yang
The development of cloud and edge computing has enabled the easy access of artificial intelligence (AI) services for massive heterogeneous and resource-constrained devices. Particularly, computation-intensive AI services can be orchestrated and deployed in the cloud or edge according to varying performance and cost requirements. Nonetheless, the improved accessibility of deep learning (DL) model variants and the evolving of computational intelligence paradigms pose great challenges for orchestrating large-scale DL inference services in the cloud-edge continuum. Focusing on cloud or edge-based deployment, existing work on multi-variant service orchestration often has a limited solution space of deployment plans. To address this limitation, we first propose a novel multi-paradigm deployment model (MPDM) for service orchestration, which not only considers the model variants but also allows the co-existence of multiple paradigms for large-scale inference service deployment. The service deployment in the MPDM model is then formulated as a multiobjective optimization problem of seeking a better tradeoff among the system accuracy, service scale, and deployment cost. To solve the multiobjective optimization, we further propose a weighted metric-based constructive heuristic algorithm (WCH), which can efficiently obtain an approximately optimal Pareto frontier. Extensive experimental results have validated the effectiveness and efficiency of WCH, and revealed the impacts of both multi-paradigm deployment and edge-cloud collaborative intelligence (ECCI) paradigm on large-scale DL serving systems.

29 May 2025 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
KLKaijia Lei
Kaijia Lei
Xuebin RenXuebin Ren
Xuebin Ren
SYShusen Yang
Shusen Yang
XWXiaocheng Wang
Xiaocheng Wang
FZFangyuan Zhao
Fangyuan Zhao
Federated Learning (FL) succeeds in collaborative and privacy-preserving ML model training among multiple distributed data owners. To maintain a healthy FL ecosystem, it is crucial to estimate the contributions of all participants fairly. Due to provable fairness, Shapley value (SV) is widely used for contribution estimation in FL. However, current studies focus on static scenarios with fixed participants and neglect the dynamic settings with the random joining or leaving of participants in practice. This paper fills the gap by proposing FedDSV, a novel contribution estimation framework for FL with dynamic participation. FedDSV supports flexible weighting mechanisms and is compatible with the SV fairness properties in dynamic scenarios. To reduce the computational complexity, we propose a Monte Carlo variant sampling method (SMC), which can adapt well to dynamic scenarios and approximate the true SVs. To evaluate the effectiveness and efficiency of our proposed approaches, extensive experiments under different settings (e.g., frequency switching, low-quality detection, etc.) are conducted on both i.i.d and non-i.i.d. distributions. Experimental results demonstrate that FedDSV can reflect the real utility contribution of data sources for dynamic FL, and SMC can approximate the exact dynamic SVs with larger similarities in a much shorter time than the state-of-the-art methods.

24 August 2024
Verified
Conference Paper
Open access
FZFangyuan Zhao
Fangyuan Zhao
ZLZitao Li
Zitao Li
Xuebin RenXuebin Ren
Xuebin Ren
BDBolin Ding
Bolin Ding
SYShusen Yang
Shusen Yang
YLYaliang Li
Yaliang Li
Data synthesis is a promising solution to share data for various downstream analytic tasks without exposing raw data. However, without a theoretical privacy guarantee, a synthetic dataset would still leak some sensitive information in raw data. As a countermeasure, differential privacy is widely adopted to safeguard data synthesis by strictly limiting the released information. This technique is advantageous yet presents significant challenges in the vertical federated setting, where data attributes are distributed among different data parties. The main challenge lies in maintaining privacy while efficiently and precisely reconstructing the correlation between attributes. In this paper, we propose a novel algorithm called VertiMRF, designed explicitly for generating synthetic data in the vertical setting and providing differential privacy protection for all information shared from data parties. We introduce techniques based on the Flajolet-Martin (FM) sketch for encoding local data satisfying differential privacy and estimating cross-party marginals. We provide theoretical privacy and utility proof for encoding in this multi-attribute data. Collecting the locally generated private Markov Random Field (MRF) and the sketches, a central server can reconstruct a global MRF, maintaining the most useful information. Two critical techniques introduced in our VertiMRF are dimension reduction and consistency enforcement, preventing the noise of FM sketch from overwhelming the information of attributes with large domain sizes when building the global MRF. These two techniques allow flexible and inconsistent binning strategies of local private MRF and the data sketching module, which can preserve information to the greatest extent. We conduct extensive experiments on four real-world datasets to evaluate the effectiveness of VertiMRF. End-to-end comparisons demonstrate the superiority of VertiMRF.

6 January 2026 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
ZZZihao Zhou
Zihao Zhou
SYShusen Yang
Shusen Yang
FZFangyuan Zhao
Fangyuan Zhao
Xuebin RenXuebin Ren
Xuebin Ren
Graph federated learning enables the collaborative extraction of high-order information from distributed subgraphs while preserving the privacy of raw data. However, graph data often exhibits overlap among different clients. Previous research has demonstrated certain benefits of overlapping data in mitigating data heterogeneity. However, the negative effects have not been explored, particularly in cases where the overlaps are imbalanced across clients. In this paper, we uncover the unfairness issue arising from imbalanced overlapping subgraphs through both empirical observations and theoretical reasoning. To address this issue, we propose FairGFL (FAIRness-aware subGraph Federated Learning), a novel algorithm that enhances cross-client fairness while maintaining model utility in a privacy-preserving manner. Specifically, FairGFL incorporates an interpretable weighted aggregation approach to enhance fairness across clients, leveraging privacy-preserving estimation of their overlapping ratios. Furthermore, FairGFL improves the tradeoff between model utility and fairness by integrating a carefully crafted regularizer into the federated composite loss function. Through extensive experiments on four benchmark graph datasets, we demonstrate that FairGFL outperforms four representative baseline algorithms in terms of both model utility and fairness.