YTYuqing Tian

Yuqing Tian

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuqing Tian has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hypergraph Attention Network for Spatio-Temporal Interference Modeling in Cellular Networks

    by Yuqing Tian, Zhaoyang Zhang, Yuzhi Yang, Ridong Li, Zhaohui Yang, Richeng Jin

    Interference is an indelible dominant feature of wireless cellular networks, which has heavy impact on the transmission quality and network capacity. While much effort has been put on the construction of radio maps that intend to characterize signal distribution with complex channel propagation models, network interference modeling remains largely overlooked, leading to incomplete and inaccurate performance evaluation in network planning and optimization. In this letter, we propose an innovative data-driven approach to characterize the spatio-temporal interference pattern, or statistical interference map, of a multi-cell network, without knowing the exact complex underlying propagation environment and traffic pattern. Specifically, a hypergraph attention network (HGAT) is designed, in which the representation of nodes and edges are inherently aligned with the overall structure and operation of a wireless network, capturing the intricate dependencies between base stations, users, radio resource blocks and the received interferences. By leveraging spatio-temporal convolution, HGAT effectively encodes network dynamics and interference characteristics, enabling accurate and robust statistical prediction. Experimental results demonstrate that our approach surpasses conventional methods in accuracy, efficiency, and scalability, marking a significant step toward intelligent and efficient wireless network planning and optimization.

  • Hierarchical Federated Edge Learning With Adaptive Clustering in Internet of Things

    by Yuqing Tian, Zhongyu Wang, Zhaoyang Zhang, Richeng Jin, Hangguan Shan, Wei Wang, Tony Q. S. Quek

    The expansion of the Internet of Things (IoT) has led to a significant surge in data flow over edge networks, posing substantial challenges to data mining and management. While federated edge learning (FEEL) effectively accomplishes global integration and local training based on the decentralized data sets, its deployment across expansive IoT networks introduces additional challenges. The primary issues stem from managing the interaction between the communication load and learning effectiveness. The communication loads driven by recurrent data exchanges between the user equipment (UE) and central servers exacerbate network congestion and latency issues. Moreover, the learning efficacy is undermined due to the typically nonindependent and identically distributed (non-IID) characteristics of real-world IoT data. In this article, a novel communication-efficient hierarchical FEEL framework is proposed to tackle these challenges. Specifically, UEs are adaptively clustered according to their link conditions, geographic locations, and data distributions. Small base stations (SBSs) collect local model updates from the UEs in their clusters and communicate with a macro base station (MBS) for the global model aggregation. To jointly maximize the communication gain (in terms of reducing latency) and the learning gain (in terms of improving accuracy), a clustering and resource allocation optimization problem is formulated, and a cross entropy-based method with low computational complexity is proposed. Numerical experiments validate that the proposed hierarchical FEEL system achieves fast convergence and significantly improves the system efficiency for various learning tasks and the system settings.


  • Unsourced Multiple Access for Mission-Critical Control Systems in Industrial Internet of Things

    by Jingze Che, Zhaoyang Zhang, Yuqing Tian, Zhaohui Yang, Ming Liu, Zhiji Deng, Xiaoming Chen

    In mission-critical Industrial Internet of Things (IIoT), multiple sensors make independent observations at different locations and then transmit them to the base station (BS) to obtain a global system state vector. Uploading observation information to the BS by active sensors is a multiple access process. As the task is to complete state estimation instead of maximizing the physical-layer capacity, conventional multiple access schemes cannot be applied directly to mission-critical IIoT applications. Therefore, next generation multiple access (NGMA) techniques are urgently needed to realize the key performance indicators for the design of IIoT networks. Note that, in mission-critical IIoT systems, each sensor can only obtain the observation of a subset of state variables, and the BS only cares about the state information embedded in that observation not the identities of the sensors. This indicates that the whole process of data transmission and state estimation can be totally unsourced, thus resulting in a highly efficient IIoT system implementation. Based on this crucial finding, in this article, we propose an unsourced multiple access (UMA)-based mission-critical IIoT system. Moreover, a decoupled UMA (D-UMA) scheme is proposed to improve transmission efficiency and state estimation performance. We analyse the fundamental aspects of how our design affects and guarantees the controllability, observability, and stability of an IIoT control system. Simulation results verify the remarkable performance of the proposed scheme compared with the conventional orthogonal multiple access (OMA) and nonorthogonal multiple access (NOMA) schemes.


  • An Edge-Cloud Collaboration Framework for Generative AI Service Provision With Synergetic Big Cloud Model and Small Edge Models

    by Yuqing Tian, Zhaoyang Zhang, Yuzhi Yang, Zirui Chen, Zhaohui Yang, Richeng Jin, Tony Q. S. Quek, Kai-Kit Wong

    Generative artificial intelligence (GenAI) offers various services to users through content creation, which is believed to be one of the most important components in future networks. However, training and deploying big artificial intelligence models (BAIMs) introduces substantial computational and communication overhead. This poses a critical challenge to centralized approaches, due to the need of high-performance computing infrastructure and the reliability, secrecy and timeliness issues in long-distance access of cloud services. Therefore, there is an urging need to decentralize the services, partly moving them from the cloud to the edge and establishing native GenAI services to enable private, timely, and personalized experiences. In this paper, we propose a brand-new bottom-up BAIM architecture with synergetic big cloud model and small edge models, and design a distributed training framework and a task-oriented deployment scheme for efficient provision of native GenAI services. The proposed framework can facilitate collaborative intelligence, enhance adaptability, gather edge knowledge and alleviate edge-cloud burden. The effectiveness of the proposed framework is demonstrated through an image generation use case. Finally, we outline fundamental research directions to fully exploit the collaborative potential of edge and cloud for native GenAI and BAIM applications.


  • Over-the-Air Split Machine Learning in Wireless MIMO Networks

    by Yuzhi Yang, Zhaoyang Zhang, Yuqing Tian, Zhaohui Yang, Chongwen Huang, Caijun Zhong, Kai-Kit Wong

    In split machine learning (ML), different partitions of a neural network (NN) are executed by different computing nodes, requiring a large amount of communication cost. As over-the-air computation (OAC) can efficiently implement all or part of the computation at the same time of communication, thus by substituting the wireless transmission in the traditional split ML framework with OAC, the communication load can be eased. In this paper, we propose to deploy split ML in a wireless multiple-input multiple-output (MIMO) communication network utilizing the intricate interplay between MIMO-based OAC and NN. The basic procedure of OAC split ML system is first provided, and we show that the inter-layer connection in a NN of any size can be mathematically decomposed into a set of linear precoding and combining transformations over a MIMO channel carrying out multi-stream analog communication. The precoding and combining matrices which are regarded as trainable parameters, and the MIMO channel matrix which are regarded as unknown (implicit) parameters, jointly serve as a fully connected layer of the NN. Most interestingly, the channel estimation procedure can be eliminated by exploiting the MIMO channel reciprocity of the forward and backward propagation, thus greatly saving the system costs and/or further improving its overall efficiency. The generalization of the proposed scheme to the conventional NNs is also introduced, i.e., the widely used convolutional neural networks. We demonstrate its effectiveness under both the static and quasi-static memory channel conditions with comprehensive simulations.


  • Top Cited Papers

    Asynchronous Federated Learning Over Wireless Communication Networks

    by Zhongyu Wang, Zhaoyang Zhang, Yuqing Tian, Qianqian Yang, Hangguan Shan, Wei Wang, Tony Q. S. Quek

    The conventional federated learning (FL) framework usually assumes synchronous reception and fusion of all the local models at the central aggregator and synchronous updating and training of the global model at all the agents as well. However, in a wireless network, due to limited radio resource, inevitable transmission failures and heterogeneous computing capacity, it is very hard to realize strict synchronization among all the involved user equipments (UEs). In this paper, we propose a novel asynchronous FL framework, which well adapts to the heterogeneity of users, communication environments and learning tasks, by considering both the possible delays in training and uploading the local models and the resultant staleness among the received models that has heavy impact on the global model fusion. A novel centralized fusion algorithm is designed to determine the fusion weight during the global update, which aims to make full use of the fresh information contained in the uploaded local models while avoiding the biased convergence by enforcing the impact of each UE’s local dataset to be proportional to its sample share. Numerical experiments validate that the proposed asynchronous FL framework can achieve fast and smooth convergence and enhance the training efficiency significantly.