Fang Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fang Shi has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Weiwei Lin
South China University of Technology
16 shared publications - Keqin Li
Hunan University
6 shared publications - Li Shen
Shenzhen Campus of Sun Yat-sen University
4 shared publications - Lisheng Fan
School of Computer Science, Guangzhou University, Guangzhou, China
4 shared publications - Wentai Wu
Jinan University
4 shared publications - Guozhi Liu
School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
3 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (10) , 12531-12543
ReSO: A Real-Time Scalable Offloading Approach for Dynamic Vehicle-to-Everything Systems
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (10) , 12531-12543
ReSO: A Real-Time Scalable Offloading Approach for Dynamic Vehicle-to-Everything Systems
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1530-1540
Decentralized Federated Learning With Period Gradient Tracking Over Time-Varying Networks
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1530-1540
Decentralized Federated Learning With Period Gradient Tracking Over Time-Varying Networks
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-13
FedPAP: Federated Learning with Personalized Adaptive Pruning
Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, but faces fundamental challenges from statistical het erogeneity, communication bottlenecks, and diverse device capabilities in wireless networks. Existing personalized FL approaches either maintain uniform model architectures or apply predefined compression strategies, failing to exploit client-specific adaptation for enhanced personalization and communication efficiency. We propose FedPAP, a personalized federated learning framework that enables each client to independently discover optimal sparse model structures tailored to local data characteristics. The core innovation is the APSF method, which efficiently determines client-specific pruning ratios through surrogate-based optimization, integrated with a personalized masked weight aggregation strategy that facilitates selective knowledge transfer among het erogeneously pruned models. We establish theoretical guarantees including generalization bounds, aggregation robustness, and convergence analysis demonstrating that FedPAP optimizes for client-specific performance rather than global consensus. Extensive experiments demonstrate that FedPAP achieves superior performance compared to state-of-the-art methods while reducing communication overhead and achieving 2-4× training speedup, with ablation studies confirming the effectiveness of adaptive pruning and robust aggregation across diverse heterogeneous scenarios.
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-13
FedPAP: Federated Learning with Personalized Adaptive Pruning
Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, but faces fundamental challenges from statistical het erogeneity, communication bottlenecks, and diverse device capabilities in wireless networks. Existing personalized FL approaches either maintain uniform model architectures or apply predefined compression strategies, failing to exploit client-specific adaptation for enhanced personalization and communication efficiency. We propose FedPAP, a personalized federated learning framework that enables each client to independently discover optimal sparse model structures tailored to local data characteristics. The core innovation is the APSF method, which efficiently determines client-specific pruning ratios through surrogate-based optimization, integrated with a personalized masked weight aggregation strategy that facilitates selective knowledge transfer among het erogeneously pruned models. We establish theoretical guarantees including generalization bounds, aggregation robustness, and convergence analysis demonstrating that FedPAP optimizes for client-specific performance rather than global consensus. Extensive experiments demonstrate that FedPAP achieves superior performance compared to state-of-the-art methods while reducing communication overhead and achieving 2-4× training speedup, with ablation studies confirming the effectiveness of adaptive pruning and robust aggregation across diverse heterogeneous scenarios.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 10120-10134
FSGDR: A Cognitive Embodied Agent Based on Fuzzy Semantic-Guided Dual-Mode Reasoning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 10120-10134
FSGDR: A Cognitive Embodied Agent Based on Fuzzy Semantic-Guided Dual-Mode Reasoning
- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (6) , 8144-8160
WSDBS: Workflow Scheduling With Dynamic Bandwidth Slicing in Resource-Constrained Edge Computing Environment
In resource-constrained edge computing, the execution efficiency of workflow applications is significantly affected by bandwidth contention, especially during data transmissions between dependent tasks. However, existing workflow scheduling studies often struggle to optimize transmission delay effectively, whereas bandwidth slicing offers promising potential by leveraging the dynamic nature of bandwidth resources. To address this issue, we propose Workflow Scheduling with Dynamic Bandwidth Slicing (WSDBS), a novel scheduling algorithm that integrates bandwidth slicing into the workflow execution process. By introducing a dual-prediction strategy, WSDBS estimates the availability of both computational and bandwidth resources on servers, facilitating efficient task scheduling decisions under transmission uncertainty. Moreover, a novel transmission urgency metric is developed, which is derived from both link load and transmission criticality. This metric guides bandwidth slicing for the dynamic allocation of server-side bandwidth resources, ultimately alleviating contention among concurrent transmissions. Extensive experiments based on real-world Alibaba cluster traces show that WSDBS consistently improves scheduling efficiency, reducing the average makespan by 10.87% –14.44% over state-of-the-art baselines. These results validate its effectiveness in alleviating bandwidth contention and improving scheduling performance in edge computing environments.
- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (6) , 8144-8160
WSDBS: Workflow Scheduling With Dynamic Bandwidth Slicing in Resource-Constrained Edge Computing Environment
In resource-constrained edge computing, the execution efficiency of workflow applications is significantly affected by bandwidth contention, especially during data transmissions between dependent tasks. However, existing workflow scheduling studies often struggle to optimize transmission delay effectively, whereas bandwidth slicing offers promising potential by leveraging the dynamic nature of bandwidth resources. To address this issue, we propose Workflow Scheduling with Dynamic Bandwidth Slicing (WSDBS), a novel scheduling algorithm that integrates bandwidth slicing into the workflow execution process. By introducing a dual-prediction strategy, WSDBS estimates the availability of both computational and bandwidth resources on servers, facilitating efficient task scheduling decisions under transmission uncertainty. Moreover, a novel transmission urgency metric is developed, which is derived from both link load and transmission criticality. This metric guides bandwidth slicing for the dynamic allocation of server-side bandwidth resources, ultimately alleviating contention among concurrent transmissions. Extensive experiments based on real-world Alibaba cluster traces show that WSDBS consistently improves scheduling efficiency, reducing the average makespan by 10.87% –14.44% over state-of-the-art baselines. These results validate its effectiveness in alleviating bandwidth contention and improving scheduling performance in edge computing environments.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (1) , 572-588
PAWSSP: A Two-Stage Parallelism-Aware Algorithm for Joint Workflow Scheduling and Service Placement in Edge Computing
In edge computing, workflow applications are optimally scheduled onto edge servers that are pre-equipped with the necessary services to satisfy stringent low-latency demands. However, prior research has not fully addressed the joint optimization of service placement and workflow scheduling, particularly the exploitation of task parallelism to reduce overall makespan. To address this shortcoming, we explore the combined workflow scheduling and service placement (WSP-SP) problem with the goal of minimizing the average makespan of applications. Recognizing that WSP-SP is NP-hard, we propose a two-stage, Parallelism Aware Workflow Scheduling and Service Placement strategy (PAWSSP) that minimizes the makespan with low complexity. In the first stage, a Parallelism Aware Service Placement module (PASP) is designed to adjust the service layout by allocating services with high parallelism onto distinct servers to fully leverage task-level concurrency. In the subsequent workflow scheduling stage, PAWSSP determines task priority by resolving inter-task competition and further reduces waiting times by assigning tasks to servers experiencing lower resource contention. We further extend PAWSSP to make it applicable to both offline and online scenarios. Extensive evaluations demonstrate that PAWSSP performs robustly across diverse scenarios, reducing the average makespan by 3.9%-14.7% compared to existing baselines, while maintaining modest runtime overhead.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (1) , 572-588
PAWSSP: A Two-Stage Parallelism-Aware Algorithm for Joint Workflow Scheduling and Service Placement in Edge Computing
In edge computing, workflow applications are optimally scheduled onto edge servers that are pre-equipped with the necessary services to satisfy stringent low-latency demands. However, prior research has not fully addressed the joint optimization of service placement and workflow scheduling, particularly the exploitation of task parallelism to reduce overall makespan. To address this shortcoming, we explore the combined workflow scheduling and service placement (WSP-SP) problem with the goal of minimizing the average makespan of applications. Recognizing that WSP-SP is NP-hard, we propose a two-stage, Parallelism Aware Workflow Scheduling and Service Placement strategy (PAWSSP) that minimizes the makespan with low complexity. In the first stage, a Parallelism Aware Service Placement module (PASP) is designed to adjust the service layout by allocating services with high parallelism onto distinct servers to fully leverage task-level concurrency. In the subsequent workflow scheduling stage, PAWSSP determines task priority by resolving inter-task competition and further reduces waiting times by assigning tasks to servers experiencing lower resource contention. We further extend PAWSSP to make it applicable to both offline and online scenarios. Extensive evaluations demonstrate that PAWSSP performs robustly across diverse scenarios, reducing the average makespan by 3.9%-14.7% compared to existing baselines, while maintaining modest runtime overhead.
- 20 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 333
Prodigal: Backdoor defense for federated learning beyond robust aggregation
- 20 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 333
Prodigal: Backdoor defense for federated learning beyond robust aggregation
- 2 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-13
AdaptiveFL: Communication-Adaptive Federated Learning Under Dynamic Bandwidth
Federated learning (FL) is a distributed machine learning paradigm that enables heterogeneous devices to train a model collaboratively. Recognizing communication as a bottleneck in FL, existing communication-efficient solutions, e.g., HeteroFL and LotteryFL, etc., utilize gradient sparsification to reduce communication costs. However, existing solutions fail to address the dynamic bandwidth issue in which the bandwidth of each client is constantly changing throughout the training process. In this article, we propose AdaptiveFL, a communication-adaptive FL framework, considering the dynamic constraints of bandwidth. The design of AdaptiveFL follows two key steps: 1) in each round, each device selects a best-fit sub-model for communication per currently available bandwidth; and 2) to guarantee the performance of each sub-model sent under dynamic bandwidth constraints, AdaptiveFL employs a local training method that enables each device to train a “tailorable” local model, which can be tailored to any sparsity with competitive accuracy. We compare AdaptiveFL with several communication-efficient SOTA methods and demonstrate that AdaptiveFL outperforms other baselines by a large margin.
- 2 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-13
AdaptiveFL: Communication-Adaptive Federated Learning Under Dynamic Bandwidth
Federated learning (FL) is a distributed machine learning paradigm that enables heterogeneous devices to train a model collaboratively. Recognizing communication as a bottleneck in FL, existing communication-efficient solutions, e.g., HeteroFL and LotteryFL, etc., utilize gradient sparsification to reduce communication costs. However, existing solutions fail to address the dynamic bandwidth issue in which the bandwidth of each client is constantly changing throughout the training process. In this article, we propose AdaptiveFL, a communication-adaptive FL framework, considering the dynamic constraints of bandwidth. The design of AdaptiveFL follows two key steps: 1) in each round, each device selects a best-fit sub-model for communication per currently available bandwidth; and 2) to guarantee the performance of each sub-model sent under dynamic bandwidth constraints, AdaptiveFL employs a local training method that enables each device to train a “tailorable” local model, which can be tailored to any sparsity with competitive accuracy. We compare AdaptiveFL with several communication-efficient SOTA methods and demonstrate that AdaptiveFL outperforms other baselines by a large margin.
- 2 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (9) , 8700-8713
Container Scheduling Strategy Based on Image Layer Reuse and Sequential Arrangement in Mobile Edge Computing
In Mobile Edge Computing (MEC) scenarios, computational tasks are popularly deployed using containerization to isolate the runtime environment. To complete the execution of the task, the edge server first pulls the image, then instantiates and runs the container. Since it takes a lot of time for the edge server to download the image from the cloud, image reuse reduces the pulling latency significantly. However, the limited storage capacity of edge servers hinders image reuse. Recent works have enhanced reuse efficiency by leveraging the hierarchical structure of images and caching high-value layers. However, their efficiency remains limited due to the lack of multi-container collaboration. This paper proposes a novel container scheduling strategy based on image layer reuse and sequence arrangement (ILR-SA) for MEC scenarios, which achieves efficient scheduling by collaborating multiple containers. First, containers are greedily deployed into the edge cluster. Then, the execution sequence of containers is modeled as an optimal Hamiltonian path problem, efficiently solved by our proposed decomposition algorithm. Finally, an efficient image layer update strategy is used to achieve layer reuse. We conduct rigorous experiments to demonstrate that our proposed container scheduling strategy reduces the computational task completion time by up to 91.3% compared to existing approaches.
- 2 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (9) , 8700-8713
Container Scheduling Strategy Based on Image Layer Reuse and Sequential Arrangement in Mobile Edge Computing
In Mobile Edge Computing (MEC) scenarios, computational tasks are popularly deployed using containerization to isolate the runtime environment. To complete the execution of the task, the edge server first pulls the image, then instantiates and runs the container. Since it takes a lot of time for the edge server to download the image from the cloud, image reuse reduces the pulling latency significantly. However, the limited storage capacity of edge servers hinders image reuse. Recent works have enhanced reuse efficiency by leveraging the hierarchical structure of images and caching high-value layers. However, their efficiency remains limited due to the lack of multi-container collaboration. This paper proposes a novel container scheduling strategy based on image layer reuse and sequence arrangement (ILR-SA) for MEC scenarios, which achieves efficient scheduling by collaborating multiple containers. First, containers are greedily deployed into the edge cluster. Then, the execution sequence of containers is modeled as an optimal Hamiltonian path problem, efficiently solved by our proposed decomposition algorithm. Finally, an efficient image layer update strategy is used to achieve layer reuse. We conduct rigorous experiments to demonstrate that our proposed container scheduling strategy reduces the computational task completion time by up to 91.3% compared to existing approaches.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (12) , 18508-18519
Dynamic Client Selection for Over-the-Air Federated Learning Network
As a privacy-preserving solution, Federated Learning (FL) demonstrates great potential in distributed model training, but limited bandwidth, particularly in NFC-based systems, emerges as a key bottleneck by restricting the number of participating clients. To address this challenge, over-the-air FL leverages the superposition property of wireless multiple-access channels, enabling faster model training and accommodating more clients, even in bandwidth-constrained scenarios like NFC. However, due to its analog-integrated nature, the FL performance is also affected by other factors, such as channel noise. These motivate us to consider how the selected client set and channel noise affect FL performance. To explore this concern, in this paper, we consider an over-the-air FL system with analog gradient aggregation and analyze the impact of the selected client set and channel noise on FL training performance. The theoretical analysis effectively shows the importance of the clients’ number and the power scaling factor to the FL training performance. Based on the theoretical analysis, we transform the global optimization problem into the client selection problem and propose a dynamic client selection scheme to optimize the training performance under the aggregation error constraint. Experimental results demonstrate that our proposed scheme can boost FL by speeding up the convergence of the global model (at least 35%) and saving energy consumption.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (12) , 18508-18519
Dynamic Client Selection for Over-the-Air Federated Learning Network
As a privacy-preserving solution, Federated Learning (FL) demonstrates great potential in distributed model training, but limited bandwidth, particularly in NFC-based systems, emerges as a key bottleneck by restricting the number of participating clients. To address this challenge, over-the-air FL leverages the superposition property of wireless multiple-access channels, enabling faster model training and accommodating more clients, even in bandwidth-constrained scenarios like NFC. However, due to its analog-integrated nature, the FL performance is also affected by other factors, such as channel noise. These motivate us to consider how the selected client set and channel noise affect FL performance. To explore this concern, in this paper, we consider an over-the-air FL system with analog gradient aggregation and analyze the impact of the selected client set and channel noise on FL training performance. The theoretical analysis effectively shows the importance of the clients’ number and the power scaling factor to the FL training performance. Based on the theoretical analysis, we transform the global optimization problem into the client selection problem and propose a dynamic client selection scheme to optimize the training performance under the aggregation error constraint. Experimental results demonstrate that our proposed scheme can boost FL by speeding up the convergence of the global model (at least 35%) and saving energy consumption.