YZYuanqiao Zhang

Yuanqiao Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuanqiao Zhang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Accountable federated learning against local poisoning attacks

    by Yuwei Wang, Yuan Gao, Yuanqiao Zhang, Haijun Geng, Haotian Chi


  • Enhancing Federated Learning With Pattern-Based Client Clustering

    by Yuan Gao, Ziyue Lin, Maoguo Gong, Yuanqiao Zhang, Yihong Zhang

    The exponential growth of the Internet of Things (IoT), driven by the increasing number of connected devices and sensors, is profoundly transforming many industries. This proliferation has been enabled by advances in storage and processing capabilities, facilitating the implementation of deep model. However, concerns surrounding privacy and substantial bandwidth required for data transmission arise from the centralized processing of data collected from numerous distributed devices. To address these issues, federated learning (FL) has emerged as a viable solution with a decentralized strategy. It ensures data privacy by allowing devices to locally train models while keeping their data localized, thus reducing centralization needs and concerns related to privacy and bandwidth. To mitigate the data heterogeneity problem in FL scenarios, we propose federated pattern extraction clustering (FedPEC) to cluster clients with similar data distributions. Compare to existing client clustering methods, FedPEC requires no additional data transmission and ensures great flexibility, scalability and privacy. Furthermore, we discuss the discrepancy between representation and data distribution in existing methods from the perspective of pattern representation. Based on this, we propose a variant of FedPEC as a solution, which has achieved excellent performance on multiple FL datasets.


  • Toward Explainable Multiparty Learning: A Contrastive Knowledge Sharing Framework

    by Yuan Gao, Yuanqiao Zhang, Maoguo Gong, Qing Cai, Yu Xie, A. K. Qin

    Multiparty learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multiparty learning approaches are confronted with obstacles, such as system heterogeneity, statistical heterogeneity, and incentive design. Determining how to deal with these challenges and further improve the efficiency and performance of multiparty learning has become an urgent problem to be solved. In this article, we propose a novel contrastive multiparty learning framework for knowledge refinement and sharing with an accountable incentive mechanism. Since the existing parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication and analogize multiparty learning as a many-to-one knowledge-sharing problem. The approach is capable of integrating the acquired explicit knowledge of each client in a transparent manner without privacy disclosure, and it reduces the dependence on data distribution and communication environments. The proposed scheme achieves significant improvement in model performance in a variety of scenarios, as we demonstrated through experiments on several real-world datasets.


  • A Multi-Modal Vertical Federated Learning Framework Based on Homomorphic Encryption

    by Maoguo Gong, Yuanqiao Zhang, Yuan Gao, A. K. Qin, Yue Wu, Shanfeng Wang, Yihong Zhang

    Federated learning has gained prominence as an effective solution for addressing data silos, enabling collaboration among multiple parties without sharing their data. However, existing federated learning algorithms often neglect the challenge posed by multi-modal data distribution. Moreover, previous pioneering work face limitations in encrypting the exponential and logarithmic operations of the objective function with multiple independent variables, and they rely on a third-party cooperator for encryption. To address these limitations, this paper introduces a universal multi-modal vertical federated learning framework. To tackle the data distribution challenge, we propose a two-step multi-modal transformer model that captures cross-domain semantic features effectively. For encryption, where traditional additively homomorphic encryption algorithms fall short by supporting only addition and multiplication, we employ bivariate Taylor series expansion to transform the objective function. Integrating these components, we present a comprehensive training and transmission protocol that eliminates the need for a third-party cooperator during the encryption process. Extensive experiments conducted on diverse video-text and image-text datasets validate the superior performance of our framework compared to state-of-the-art approaches, affirming its effectiveness in multi-modal vertical federated learning settings.


  • Heterogeneous Multi-Party Learning With Data-Driven Network Sampling

    by Maoguo Gong, Yuan Gao, Yue Wu, Yuanqiao Zhang, A. K. Qin, Yew-Soon Ong

    Multi-party learning provides an effective approach for training a machine learning model, e.g., deep neural networks (DNNs), over decentralized data by leveraging multiple decentralized computing devices, subjected to legal and practical constraints. Different parties, so-called local participants, usually provide heterogenous data in a decentralized mode, leading to non-IID data distributions across different local participants which pose a notorious challenge for multi-party learning. To address this challenge, we propose a novel heterogeneous differentiable sampling (HDS) framework. Inspired by the dropout strategy in DNNs, a data-driven network sampling strategy is devised in the HDS framework, with differentiable sampling rates which allow each local participant to extract from a common global model the optimal local model that best adapts to its own data properties so that the size of the local model can be significantly reduced to enable more efficient inference. Meanwhile, co-adaptation of the global model via learning such local models allows for achieving better learning performance under non-IID data distributions and speeds up the convergence of the global model. Experiments have demonstrated the superiority of the proposed method over several popular multi-party learning techniques in the multi-party settings with non-IID data distributions.


  • Device-Performance-Driven Heterogeneous Multiparty Learning for Arbitrary Images

    by Yuanqiao Zhang, Maoguo Gong, Yuan Gao, A. K. Qin, Kun Wang, Yiming Lin, Shanfeng Wang

    Multiparty learning (MPL) is an emerging framework for privacy-preserving collaborative learning. It enables individual devices to build a knowledge-shared model and remaining sensitive data locally. However, with the continuous increase of users, the heterogeneity gap between data and equipment becomes wider, which leads to the problem of model heterogeneous. In this article, we concentrate on two practical issues: data heterogeneous problem and model heterogeneous problem, and propose a novel personal MPL method named device-performance-driven heterogeneous MPL (HMPL). First, facing the data heterogeneous problem, we focus on the problem of various devices holding arbitrary data sizes. We introduce a heterogeneous feature-map integration method to adaptively unify the various feature maps. Meanwhile, to handle the model heterogeneous problem, as it is essential to customize models for adapting to the various computing performances, we propose a layer-wise model generation and aggregation strategy. The method can generate customized models based on the device’s performance. In the aggregation process, the shared model parameters are updated through the rules that the network layers with the same semantics are aggregated with each other. Extensive experiments are conducted on four popular datasets, and the result demonstrates that our proposed framework outperforms the state of the art (SOTA).

  • MMPL: Multi-Objective Multi-Party Learning via Diverse Steps

    by Yuanqiao Zhang, Maoguo Gong, Yuan Gao, Hao Li, Lei Wang, Yixin Wang

    Multi-party learning is a specific framework of distributed learning which is widely exploited in the medical system and mobile data analysis. By installing a central server, individual devices update the model parameters instead of sharing sensitive data. This method can protect data privacy with the highest measures. But during the communication round, it is difficult to balance the model performance and the computational costs. In this article, we propose a novel framework for multiparty learning, named Multi-objective Multi-Party Learning via Diverse Steps (MMPL). We regard multi-party learning as a multi-objective problem and employ evolutionary optimization for analysis. Within the design of our framework, we try to use the neural network as a bridge to connect evolutionary optimization with multi-party learning. During the study, we propose a novel space-searching strategy for complex encoding problems. An individual wised value is installed on each private device for a differentiated treatment. Experimental results between our method and the comparative algorithms show that the proposed algorithm can achieve better performance while partly ameliorating the time-consuming problem.


  • Federated Learning on Multimodal Data: A Comprehensive Survey

    by Yi-Ming Lin, Yuan Gao, Mao-Guo Gong, Si-Jia Zhang, Yuan-Qiao Zhang, Zhi-Yuan Li

    With the growing awareness of data privacy, federated learning (FL) has gained increasing attention in recent years as a major paradigm for training models with privacy protection in mind, which allows building models in a collaborative but private way without exchanging data. However, most FL clients are currently unimodal. With the rise of edge computing, various types of sensors and wearable devices generate a large amount of data from different modalities, which has inspired research efforts in multimodal federated learning (MMFL). In this survey, we explore the area of MMFL to address the fundamental challenges of FL on multimodal data. First, we analyse the key motivations for MMFL. Second, the currently proposed MMFL methods are technically classified according to the modality distributions and modality annotations in MMFL. Then, we discuss the datasets and application scenarios of MMFL. Finally, we highlight the limitations and challenges of MMFL and provide insights and methods for future research.


  • Landslide Inventory Mapping Method Based on Adaptive Histogram-Mean Distance With Bitemporal VHR Aerial Images

    by Tongfei Liu, Maoguo Gong, Fenlong Jiang, Yuanqiao Zhang, Hao Li

    Landslide inventory mapping (LIM) on the basis of change detection techniques has potential significance for landslide disaster analysis. In this letter, a novel LIM approach based on the adaptive histogram-mean distance (AHMD) is proposed, which adaptively considers spatial contextual information of different landslide regions to improve the detection performance. First, to adapt the shape, size, and distribution of various landslides, an adaptive region around a pixel is extracted by a novel adaptive region extension algorithm without parameter setting. Second, the pixels within the adaptive region are taken to construct the spectral frequency histograms, and then, the adaptive histogram mean (AHM) is developed as the feature of a histogram. Third, the AHMD is defined based on the bin-to-bin (B2B) distance to measure change magnitude between the pairwise AHMs. Finally, LIM can be obtained by a supervised threshold method called double-window flexible pace search (DFPS). Experimental results tested on two real datasets with a very high spatial resolution (VHR) demonstrate the outperformance of the proposed AHMD approach with seven comparative methods.