Constructing Multimodal Wireless Knowledge Graphs for Large Language Model–Based Network Reasoning
DOI:
https://doi.org/10.65455/1bt00146关键词:
Knowledge Graph, Retrieval-Augmented Generation, Wireless Networks, Large Language Models, Graph-Based Retrieval摘要
The increasing complexity of wireless networks and the proliferation of heterogeneous data sources pose significant challenges to intelligent network management and decision-making. Although Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, their direct application in wireless network tasks is limited due to the lack of structured domain knowledge and reliable contextual foundations. This paper proposes an intelligent knowledge graph enhanced retrieval-enhanced generation (KG-RAG) framework for multimodal wireless networks. First, through structured entity and relationship modeling, multimodal wireless data including network measurements, configuration parameters and domain knowledge are transformed into a unified knowledge graph. The constructed knowledge graph, as a clear semantic backbone, supports efficient knowledge retrieval and reasoning. By integrating graph-based retrieval results with LLMs, the proposed framework achieves context-aware and interpretable network reasoning. The effectiveness of this method is evaluated through a case study based on lightweight network slicing. The experimental results show that in different LLMs, compared with the traditional text-based RAG method, the KG-enhanced RAG method improves the reasoning accuracy, reasoning consistency and interpretive integrity. These findings indicate that structured knowledge representation plays a crucial role in enhancing the reliability and interpretability of LLM-driven wireless network intelligence.
参考
[1]ODIDA M O. The evolution of mobile communication: A comprehensive survey on 5G technology. Journal of Sensor Networks and Data Communications, 2024, 4(1): 1-11. DOI: https://doi.org/10.33140/JSNDC.04.01.06
[2]XU Z, LV Z, CHU B, et al. Progress and prospects of future urban health status prediction. Engineering Applications of Artificial Intelligence, 2024, 129: 107573. DOI: https://doi.org/10.1016/j.engappai.2023.107573
[3]MAO S, LIU L, HOU X, et al. Multi-domain resource management for space–air–ground integrated sensing, communication, and computation networks. IEEE Journal on Selected Areas in Communications, 2024, 42(12): 3380-3394. DOI: https://doi.org/10.1109/JSAC.2024.3459026
[4]NAZAR A M, SELIM M Y, QIAO D, et al. NextG-GPT: Leveraging GenAI for Advancing Wireless Networks and Communication Research//2025 34th International Conference on Computer Communications and Networks (ICCCN). New York: IEEE, 2025: 1-9. DOI: https://doi.org/10.1109/ICCCN65249.2025.11133874
[5]ZHU X, XIE Y, LIU Y, et al. Knowledge graph-guided retrieval augmented generation//Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Stroudsburg: Association for Computational Linguistics, 2025: 8912-8924. DOI: https://doi.org/10.18653/v1/2025.naacl-long.449
[6]MAVROMATIS C, KARYPIS G. Gnn-rag: Graph neural retrieval for large language model reasoning. arXiv preprint, 2024. DOI: https://doi.org/10.18653/v1/2025.findings-acl.856
[7]YUAN D, ZHOU H, WU D, et al. Enhancing large language models (llms) for telecommunications using knowledge graphs and retrieval-augmented generation//2025 IEEE International Conference on Communications Workshops (ICC Workshops). New York: IEEE, 2025: 486-491. DOI: https://doi.org/10.1109/ICCWorkshops67674.2025.11162336
[8]HUANG Y, YOU X, ZHAN H, et al. Learning wireless data knowledge graph for green intelligent communications: Methodology and experiments. IEEE Transactions on Mobile Computing, 2024, 23(12): 12298-12312. DOI: https://doi.org/10.1109/TMC.2024.3408142
[9]LIU S, ZHANG T, FU N, et al. Fine-grained graph representation learning for heterogeneous mobile networks with attentive fusion and contrastive learning//Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, No. 18. Washington, DC: AAAI Press, 2025: 18933-18942. DOI: https://doi.org/10.1609/aaai.v39i18.34084
[10]DAI Y, LYU L, CHENG N, et al. A survey of graph-based resource management in wireless networks—Part II: Learning approaches. IEEE Transactions on Cognitive Communications and Networking, 2024, 11(4): 2101-2122. DOI: https://doi.org/10.1109/TCCN.2024.3508777
[11]XU Z, LV Z, LI J, et al. A novel perspective on travel demand prediction considering natural environmental and socioeconomic factors. IEEE Intelligent Transportation Systems Magazine, 2022, 15(1): 136-159. DOI: https://doi.org/10.1109/MITS.2022.3162901
[12]LV Z, LI J, DONG C, et al. Deep learning in the COVID-19 epidemic: A deep model for urban traffic revitalization index. Data & Knowledge Engineering, 2021, 135: 101912. DOI: https://doi.org/10.1016/j.datak.2021.101912
[13]SHENG Z, LV Z, LI J, et al. Deep spatial-temporal travel time prediction model based on trajectory feature. Computers and Electrical Engineering, 2023, 110: 108868. DOI: https://doi.org/10.1016/j.compeleceng.2023.108868
[14]YAN H, LI J, CHU B, et al. HT-STNet: a hierarchical Tucker decomposition and spatio-temporal LSTM network for accurate and efficient shared mobility demand forecasting on sparse data. Applied Intelligence, 2025, 55(7): 631. DOI: https://doi.org/10.1007/s10489-025-06500-7
[15]YUAN G, LI J, LV Z, et al. DDCAttNet: road segmentation network for remote sensing images//International Conference on Wireless Algorithms, Systems, and Applications. Cham: Springer International Publishing, 2021: 457-468. DOI: https://doi.org/10.1007/978-3-030-86130-8_36
[16]LI J, LV Z, MA Z, et al. Optimization of spatial-temporal graph: A taxi demand forecasting model based on spatial-temporal tree. Information Fusion, 2024, 104: 102178. DOI: https://doi.org/10.1016/j.inffus.2023.102178
[17]ZHAO M, ZHANG Y, LIU Q, et al. AdaSlicing: Adaptive online network slicing under continual network dynamics in open radio access networks//IEEE INFOCOM 2025-IEEE Conference on Computer Communications. New York: IEEE, 2025: 1-10. DOI: https://doi.org/10.1109/INFOCOM55648.2025.11044475
[18]LIU Z. Explainable machine learning for telecom customer churn prediction and actionable retention strategies. Applied Artificial Intelligence Research, 2026, 2(1).
[19]ZHOU J. Personalized recommendation algorithms in digital media: A review of engagement effects, information cocoons, and marketing implications. Applied Artificial Intelligence Research, 2026, 2(1). DOI: https://doi.org/10.65455/qnpjvg49
[20]LI M, MIAO S, LI P. Simple is effective: The roles of graphs and large language models in knowledge-graph-based retrieval-augmented generation. arXiv preprint, 2024.
[21]LIU Z. Explainable machine learning for telecom customer churn prediction and actionable retention strategies. Applied Artificial Intelligence Research, 2026, 2(1). DOI: https://doi.org/10.65455/1z4v1627
[22]LI L. Map of geographical science based on artificial intelligence. Applied Artificial Intelligence Research, 2025, 1(3). DOI: https://doi.org/10.65455/dhsph777
[23]NIE H. Ethics-first lightweight AI: Differentiated English teaching and cultural competence in junior middle schools. Applied Artificial Intelligence Research, 2025, 1(3). DOI: https://doi.org/10.65455/es208a12
[24]LUO H, YAN Y, BIAN Y, et al. Ai reasoning for wireless communications and networking: A survey and perspectives. arXiv preprint, 2025. DOI: https://doi.org/10.1145/3811822
[25]BARONA LÓPEZ L I, BORJA SALTOS T. Heterogeneity challenges of federated learning for future wireless communication networks. Journal of Sensor and Actuator Networks, 2025, 14(2): 37. DOI: https://doi.org/10.3390/jsan14020037
[26]JADAV N K, NAIR A R, GUPTA R, et al. AI‐driven network softwarization scheme for efficient message exchange in IoT environment beyond 5G. International Journal of Communication Systems, 2025, 38(1): e5336. DOI: https://doi.org/10.1002/dac.5336
[27]MOU D. A comprehensive survey of deep learning–based object tracking for augmented reality in complex real-world scenes. Applied Artificial Intelligence Research, 2026, 2(1). DOI: https://doi.org/10.65455/ddjkhy91
[28]AOUEDI O, LE V A, PIAMRAT K, et al. Deep learning on network traffic prediction: Recent advances, analysis, and future directions. ACM Computing Surveys, 2025, 57(6): 1-37. DOI: https://doi.org/10.1145/3703447
[29]YE R, XU Z, PANG J. DDFM: A novel perspective on urban travel demand forecasting based on the ensemble empirical mode decomposition and deep learning//Proceedings of the 5th International Conference on Big Data Technologies. New York: ACM, 2022: 373-379. DOI: https://doi.org/10.1145/3565291.3565351
[30]YE S, WU Q, FAN P, et al. A survey on semantic communications in internet of vehicles. Entropy, 2025, 27(4): 445. DOI: https://doi.org/10.3390/e27040445
[31]SHA X, LI B, ZHAO Z, et al. How Does Population Aging Affect New Quality Productivity in Economic Sustainability? An Empirical Study Based on Mediating Mechanisms and Moderating Effects. Sustainability, 2025, 17(18): 8249. DOI: https://doi.org/10.3390/su17188249
[32]SUN H, LV Z, LI J, et al. Prediction of cancellation probability of online car-hailing orders based on multi-source heterogeneous data fusion//International Conference on Wireless Algorithms, Systems, and Applications. Cham: Springer Nature Switzerland, 2022: 168-180. DOI: https://doi.org/10.1007/978-3-031-19214-2_14
[33]LV Z, CHENG Z, LI J, et al. TreeCN: time series prediction with the tree convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems, 2023, 25(5): 3751-3766. DOI: https://doi.org/10.1109/TITS.2023.3325817
[34]LI H, LI J, LV Z, et al. MFAGCN: multi-feature based attention graph convolutional network for traffic prediction//International Conference on Wireless Algorithms, Systems, and Applications. Cham: Springer International Publishing, 2021: 227-239. DOI: https://doi.org/10.1007/978-3-030-85928-2_18
[35]XU Z, LV Z, CHU B, et al. Fast autoregressive tensor decomposition for online real-time traffic flow prediction. Knowledge-Based Systems, 2023, 282: 111125. DOI: https://doi.org/10.1016/j.knosys.2023.111125
[36]AMUGONGO L M, MASCHERONI P, BROOKS S, et al. Retrieval augmented generation for large language models in healthcare: A systematic review. PLOS Digital Health, 2025, 4(6): e0000877. DOI: https://doi.org/10.1371/journal.pdig.0000877
##submission.downloads##
已出版
##submission.dataAvailability##
The data that support the findings of this study are available from the corresponding author upon reasonable request.
期次
栏目
##submission.license##
##submission.copyrightStatement##
##submission.license.cc.by4.footer##