YFYanfang Fan

Yanfang Fan

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yanfang Fan has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    HKG-RAG: An Adaptive Retrieval-Augmented Generation Framework with Hierarchical Knowledge Graphs and Multi-Agent Collaboration

    by Ruoyu Chen, Jingqi Wang, Xiaoye He, Yanfang Fan, Ying Cai, Yuhang Guo, Zhenghao Ji, Haitao Li

    Naive retrieval-augmented generation (RAG) built upon vector retrieval still suffers from limitations when processing queries demanding complex multi-hop reasoning or global comprehension of the knowledge base. To address these limitations, existing studies have incorporated knowledge graphs into RAG and further explored hierarchical knowledge organization, for instance via multi-level summaries. However, existing methods still face two major limitations. First, their retrieval strategies are relatively rigid, and the retrieval process lacks sufficient awareness of graph structure, making it difficult to fully exploit hierarchical knowledge organization during retrieval. Second, they exhibit limited capability for reasoning over multi-granularity knowledge and lack differentiated retrieval and reasoning strategies for queries of varying granularity. To address these challenges, we propose HKG-RAG, an adaptive RAG framework that integrates hierarchical knowledge graphs with multi-agent collaboration. HKG-RAG constructs a hierarchical knowledge graph through document information extraction, entity-relation modeling, and document topic clustering. It further introduces a collaborative question-answering workflow consisting of a QuestionAnalysis agent, a RetrievalDecision agent, and an AnswerEvaluation agent. Guided by query characteristics, the workflow performs multi-granularity knowledge retrieval by dynamically selecting among document-chunk retrieval, entity retrieval, entity-relation retrieval, and topic retrieval, and iteratively refines its retrieval strategy based on evaluation feedback. Experiments on public question-answering benchmark datasets spanning four domains and a self-constructed private-domain dataset demonstrate that HKG-RAG effectively improves question-answering quality.The source code and dataset will be made publicly available upon publication.

  • Open Access

    Blockchain-Based Data Sharing in the Internet of Vehicles: A Survey

    by Yanfang Fan, Yuhang Guo, Yinglun Sun, Zhe Zhang

    Data sharing in the Internet of Vehicles (IoV), which refers to the exchange and sharing of traffic data among vehicles and between vehicles and infrastructure, can significantly improve driving experience and enhance driving safety. By virtue of decentralization, tamper-proofing, and traceability, blockchain has been widely used in IoV data sharing, providing a reliable foundation for establishing a trusted data sharing environment. However, the integration of traditional blockchain and IoV data sharing still encounters several non-negligible challenges. This paper presents a systematic overview of blockchain-based data sharing schemes in IoV and summarizes the main challenges. We then analyze and compare existing solutions for three critical issues: low transactions per second (TPS) performance, high storage overhead, and insufficient incentives. Finally, combined with the development trends of IoV and blockchain technologies, we propose potential future research directions.

  • Open Access

    Vehicle Collaborative Partial Offloading Strategy in Vehicular Edge Computing

    by Ruoyu Chen, Yanfang Fan, Shuang Yuan, Yanbo Hao

    Vehicular Edge Computing (VEC) is a crucial application of Mobile Edge Computing (MEC) in vehicular networks. In VEC networks, the computation tasks of vehicle terminals (VTs) can be offloaded to nearby MEC servers, overcoming the limitations of VTs’ processing power and reducing latency caused by distant cloud communication. However, a mismatch between VTs’ demanding tasks and MEC servers’ limited resources can overload MEC servers, impacting Quality of Service (QoS) for computationally intensive tasks. Additionally, vehicle mobility can disrupt communication with static MEC servers, further affecting VTs’ QoS. To address these challenges, this paper proposes a vehicle collaborative partial computation offloading model. This model allows VTs to offload tasks to two types of service nodes: collaborative vehicles and MEC servers. Factors like a vehicle’s mobility, remaining battery power, and available computational power are also considered when evaluating its suitability for collaborative offloading. Furthermore, we design a deep reinforcement learning-based strategy for collaborative partial computation offloading that minimizes overall task delay while meeting individual latency constraints. Experimental results demonstrate that compared to traditional approaches without vehicle collaboration, this scheme significantly reduces latency and achieves a significant reduction (around 2%) in the failure rate under tighter latency constraints.


  • Open Access

    A Game-Theoretic Scheme for Parked Vehicle-Assisted MEC Computation Offloading

    by Ruoyu Chen, Yanfang Fan, Mengxin Jia, Shuang Yuan

    By offloading computation tasks, multi-access edge computing (MEC) supports diverse services and reduces delay and energy consumption of mobile devices (MDs). However, limited resources of edge servers may be the bottleneck for task computing in high-density scenarios. To address this challenge, by leveraging the underutilized resources of parked vehicles to execute tasks, we propose a parked vehicle-assisted multi-access edge computing (PV-assisted MEC) architecture, which enables MEC servers to expand their capability flexibly. To achieve efficient offloading, we propose a PV-assisted MEC offloading scheme in a multi-MD environment. We design a game-based distributed algorithm to minimize the overhead of MDs and further reduce the burden on the MEC server. Simulation results show that compared with the common MEC system, our scheme can reduce the burden on the MEC server by 5% and the offloading overhead by 17%.