计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (9): 145-156.doi: 10.11896/jsjkx.250800036

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于硬提示的多模态新能源数据特征图建模方法

王星越1, 叶宏庭1, 许洪华2, 周苏洋3, 孔佑勇1   

  1. 1 东南大学计算机科学与工程学院 南京 211189
    2 国网江苏省电力有限公司南京供电分公司 南京 210008
    3 东南大学电气工程学院 南京 210096
  • 收稿日期:2025-08-11 修回日期:2025-11-26 出版日期:2026-09-15 发布日期:2026-09-10
  • 通讯作者: 孔佑勇(kongyouyong@seu.edu.cn)
  • 作者简介:(220242289@seu.edu.cn)
  • 基金资助:
    国家电网公司总部科技项目(5700-202499327A-1-3-ZB)

Multimodal Renewable Energy Data Feature Graph Modeling Method Based on Hard Prompts

WANG Xingyue1, YE Hongting1, XU Honghua2, ZHOU Suyang3, KONG Youyong1   

  1. 1 School of Computer Science and Engineering,Southeast University,Nanjing 211189,China
    2 Nanjing Power Supply Branch of State Grid Corporation of China,Nanjing 210008,China
    3 School of Electrical Engineering,Southeast University,Nanjing 210096,China
  • Received:2025-08-11 Revised:2025-11-26 Published:2026-09-15 Online:2026-09-10
  • About author:WANG Xingyue,born in 2002,postgra-duate.His main research interests include large language model and spatial-temporal forecasting.
    KONG Youyong,born in 1987,associate professor,Ph.D supervisor.His main research interests include artificial intelligence,large language model and cross application.
  • Supported by:
    State Grid Corporation of China Headquarters Technology Project (5700-202499327A-1-3-ZB).

PDF (PC)

326

摘要： 为满足新能源发电并网与建设智能电网的需求,研究新能源数据特征图建模方法具有重大意义。图结构数据能建模真实世界中的各类系统,在各个领域被广泛应用。但是,图结构数据复杂的非欧几何特性与标注数据的稀缺性对图神经网络的泛化能力提出了严峻挑战。传统监督学习依赖大规模标注数据,而“预训练、微调”范式又存在优化目标不一致和全量参数微调开销大的双重瓶颈。近年来,提示学习通过任务对齐与参数高效微调为突破上述瓶颈提供了新的思路,但现有图提示方法仍面临跨领域适配能力弱的共性问题。针对该问题,提出基于硬提示的多模态新能源数据特征图建模方法,利用文本属性图,通过自然语言的方式对多模态新能源数据进行统一描述,并结合大语言模型进行语义特征嵌入学习,使模型能够有效提取不同特征的语义表征,实现多模态新能源数据特征的语义一致性建模。同时,在图结构的构建上提出提示节点与类别节点的创新,以统一多领域多任务图任务的目标一致性,并为模型提供指导信息。此外,采用交替训练策略提升训练效率并增强模型的泛化能力。在5个图数据集和一个新能源风电数据集上的实验验证了所提方法的有效性,说明基于硬提示的多模态新能源数据特征图建模方法能够对包含新能源数据的多模态数据特征进行图建模。

关键词: 图神经网络, 预训练, 微调, 提示学习, 通用模型

Abstract: To meet the requirements of grid connection of renewable energy power generation and the construction of smart grids,research on feature graph modeling methods for renewable energy data is of great significance.Graph-structured data can model various real-world systems and is widely used in various fields.However,the complex non-Euclidean geometry of graph-structured data and the scarcity of annotated data pose severe challenges to the generalization ability of graph neural networks.Traditional supervised learning relies on large-scale annotated data,while the “pre-training and fine-tuning” paradigm suffers from the dual bottlenecks of inconsistent optimization objectives and high overhead of full parameter fine-tuning.In recent years,prompt learning has provided new approaches to overcome these bottlenecks by aligning tasks and efficiently fine-tuning parameters.However,existing graph prompting methods still suffer from the common problem of poor cross-domain adaptability.To address this issue,this paper proposes a multimodal renewable energy data feature graph modeling method based on hard prompts.This method uses a text attribute graph to uniformly describe multimodal renewable energy data using natural language.It then integrates a large language model to learn semantic feature embedding.This enables the model to effectively extract semantic representations of different features,achieving semantically consistent modeling of multimodal renewable energy data features.This method also innovates the construction of graph structures by introducing prompt nodes and category nodes to unify the goals of multi-domain and multi-task graph tasks and provide guidance for the model.Furthermore,this method employs an alternating training strategy to improve training efficiency and enhance the model’s generalization capabilities.Experiments on five graph datasets and one renewable energy wind power dataset validate the effectiveness of this method,demonstrating its ability to graph model multimodal data features,including renewable energy data.

Key words: Graph neural networks, Pre-training, Fine-tuning, Prompt learning, General models

中图分类号: 

  • TP391
[1] ZHANG X,WANG Z,LI J,et al.Key node identification in temporal social networks based on deep learning and multi-feature fusion[J].Computer Science,2026,53(4):143-154.
[2] WANG Z,LIU M,LUO Y,et al.Advanced graph and sequence neural networks for molecular property prediction and drug discovery[J].Bioinformatics,2022,38(9):2579-2586.
[3] FENG N,GUO S,SONG C,et al.Multi-component spatial-temporal graph convolution networks fortraffic flow forecasting[J].Journal of Software,2019,30(3):759-769.
[4] WANG R,YAN Y,WANG J,et al.Acekg:A large-scale know-ledge graph for academic data mining[C] //Proceedings of the 27th ACM International Conference on Information and Know-ledge Management.2018:1487-1490.
[5] ZHANG H,WANG X,HAN L,et al.Research on Question Answering System on Joint of Knowledge Graph and Large Language Models[J].Journal of Frontiers of Computer Science and Technology,2023,17(10):2377-2388.
[6] YING R,HE R,CHEN K,et al.Graph convolutional neural networks for web-scale recommender systems[C] //Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:974-983.
[7] ZHANG C,SONG D,HUANG C,et al.Heterogeneous graph neural network[C] //.Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mi-ning.2019:793-803.
[8] WU Y,WANG Y,WANG X,et al.Motif-Based Hypergraph Convolution Network for Semi-SupervisedNode Classification on Heterogeneous Graph[J].Chinese Journal of Computers,2021,44(11):2248-2260.
[9] ZHANG M,CHEN Y.Link prediction based on graph neural networks[C] //Proceedings of the 32nd International Conference on Neural Information Processing Systems.2018:5171-5181.
[10] WANG Z,SHEN H,CAO Q,et al.Survey on Graph Classification[J].Journal of Software,2022,33(1):171-192.
[11] XIE Y,WANG Z,YANG C,et al.Komen:Domain knowledge guided interaction recommendation for emerging scenarios[C] //Proceedings of the ACM Web Conference 2022.2022:1301-1310.
[12] LU W,WU Q,ZHANG J,et al.Tankbind:Trigonometry-aware neural networks for drugprotein binding structure prediction[J].Advances in Neural Information Processing Systems,2022,35:7236-7249.
[13] KRIEGE N M,JOHANSSON F D,MORRIS C.A survey on graph kernels[J].Applied Network Science,2020,5:1-42.
[14] PLATT J C.Fast training of support vector machines using sequential minimal optimization [M].MIT Press,1999:185-208.
[15] XU B,CEN K,HUANG J,et al.A Survey on Graph Convolutional Neural Network[J].Chinese Journal of Computers,2020,43(5):755-780.
[16] GILMER J,SCHOENHOLZ S S,RILEY P F,et al.Neural message passing for quantum chemistry[C] //International Confe-rence on Machine Learning.PMLR,2017:1263-1272.
[17] KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[C] //International Conference on Learning Representations.2017.
[18] VELICKOVIC P,CUCURULL G,CASANOVA A,et al.Graph attention networks[C] //ICLR.2018.
[19] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C] //Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[20] DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[C] //Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,.2019:4171-4186.
[21] BROWN T,MANN B,RYDER N,et al.Language models are few-shot learners[J].Advances in Neural Information Proces-sing Systems,2020,33:1877-1901.
[22] WU Z,JAIN P,WRIGHT M,et al.Representing long-range context for graph neural networks with global attention[J].Advances in Neural Information Processing Systems,2021,34:13266-13279.
[23] CHEN D,O’BRAY L,BORGWARDT K.Structure-awaretransformer for graph representation learning[C] //International Conference on Machine Learning.PMLR,2022:3469-3489.
[24] YING C,CAI T,LUO S,et al.Do transformers really perform badly for graph representation?[J].Advances in neural information processing systems,2021,34:28877-28888.
[25] ZHU Y,XU Y,YU F,et al.Graph contrastive learning withadaptive augmentation[C] //Proceedings of the Web Conference 2021.2021:2069-2080.
[26] HOU Z,LIU X,CEN Y,et al.Graphmae:Self-supervisedmasked graph autoencoders[C] //Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mi-ning.2022:594-604.
[27] YOU Y,CHEN T,SUI Y,et al.Graph contrastive learning with augmentations[J].Advances in Neural Information Processing Systems,2020,33:5812-5823.
[28] XIA J,WU L,CHEN J,et al.Simgrace:A simple framework for graph contrastive learning without data augmentation[C] //Proceedings of the ACM Web Conference 2022.2022:1070-1079.
[29] LIU P,YUAN W,FU J,et al.Pre-train,prompt,and predict:A systematic survey of prompting methods in natural language processing[J].ACM Computing Surveys,2023,55(9):1-35.
[30] SUN M,ZHOU K,HE X,et al.Gppt:Graph pre-training andprompt tuning to generalize graph neural networks[C] //Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2022:1717-1727.
[31] LIU Z,YU X,FANG Y,et al.Graphprompt:Unifying pre-training and downstream tasks for graph neural networks[C] //Proceedings of the ACM Web Conference 2023.2023:417-428.
[32] FANG T,ZHANG Y,YANG Y,et al.Universal prompt tuning for graph neural networks[J].Advances in Neural Information Processing Systems,2023,36:52464-52489.
[33] SUN X,CHENG H,LI J,et al.All in one:Multi-task prompting for graph neural networks[C] //Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2023:2120-2131.
[34] YU J,LIU Y,ZHANG Y,et al.Survey on Large-Scale Graph Pattern Matching[J].Journal of Computer Research and Deve-lopment,2015,52(2):391-409.
[35] SHERVASHIDZE N,SCHWEITZER P,VAN LEEUWEN EJ,et al.Weisfeiler-lehman graph kernels[J].Journal of Machine Learning Research,2011,12:2539-2561.
[36] BUNKE H.On a relation between graph edit distance and maximum common subgraph[J].Pattern Recognition Letters,1997,18(8):689-694.
[37] HAMMOND D K,VANDERGHEYNST P,GRIBONVAL R.Wavelets on graphs via spectral graph theory[J].Applied and Computational Harmonic Analysis,2011,30(2):129-150.
[38] HAMILTON W L,YING R,LESKOVEC J.Inductive representation learning on large graphs[C] //Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:1025-1035.
[39] XU K,HU W,LESKOVEC J,et al.How powerful are graphneural networks?[C] //International Conference on Learning Representations.2019.
[40] DWIVEDI V P,BRESSON X.A generalization of transformer networks to graphs[J].arXiv:2012.09699,2020.
[41] YAN Y,ZHANG P,FANG Z,et al.Inductive graph alignment prompt:bridging the gap between graph pre-training and inductive fine-tuning from spectral perspective[C] //Proceedings of the ACM Web Conference 2024.2024:4328-4339.
[42] HOU Z,HE Y,CEN Y,et al.Graphmae2:A decoding-enhanced masked self-supervised graph learner[C] //Proceedings of the ACM Web Conference 2023.2023:737-746.
[43] YU B,CAI X,WEI J.Few-shot text classification method based on prompt learning[J].Journal of Computer Applications,2023,43(9):2735-2740.
[44] WANG R,WU F,ZHANG B.Multi-label Image Classification Method Based on Prompt Learning and Attention Mechanism[J].Software Engineering,2024,27(7):42-46.
[45] ZHANG D,WAN W.Fine-Tuning via Mask Language ModelEnhanced Representations Based Contrastive Learning and Application[J].Computer Engineering and Applications,2024,60(17):129-138.
[46] SEN P,NAMATA G,BILGIC M,et al.Collective classification in network data[J].AI magazine,2008,29(3):93.
[47] BORDES A,USUNIER N,GARCIA-DURÁN A,et al.Translating embeddings for modeling multirelational data[C] //Procee-dings of the 27th International Conference on Neural Information Processing Systems.2013:2787-2795.
[48] WU Z,RAMSUNDAR B,FEINBERG E N,et al.Moleculenet:a benchmark for molecular machine learning[J].ChemicalScience,2018,9(2):513-530.
[49] MERNYEI P,CANGEA C.Wiki-cs:A wikipedia-based bench-mark for graph neural networks[J].arXiv:2007.02901,2020.
[50] YANG X,YAN M,PAN S,et al.Simple and efficient heterogeneous graph neural network[J].Proceedings of the AAAI Conference on Artificial Intelligence,2023,37(9):10816-10824.
[51] HE M,WEI Z,FENG S,et al.Spectral heterogeneous graphconvolutions via positive noncommutative polynomials[C] //Proceedings of the ACM Web Conference 2024.2024:685-696.
[52] REIMERS N,GUREVYCH I.Sentence-BERT:Sentence em-beddings using Siamese BERTnetworks[C] //Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:3982-3992.
[53] HE P,LIU X,GAO J,et al.Deberta:Decoding-enhanced bert with disentangled attention[J].arXiv:2006.03654,2020.
[54] TOUVRON H,LAVRIL T,IZACARD G,et al.Llama:Openand efficient foundation language models[J].arXiv:2302.13971,2023.
[55] YANG A,YANG B,ZHANG B,et al.Qwen2.5 technical report[J].arXiv:2412.15115,2024.
[56] GUO D,YANG D,ZHANG H,et al.Deepseek-r1:Incentivizing reasoning capability in llms via reinforcement learning[J].ar-Xiv:2501.12948,2025.
[57] GLOROT X,BORDES A,BENGIO Y.Deep sparse rectifierneural networks[C] //Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics.JMLR Workshop and Conference Proceedings,2011:315-323.
[58] KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014.
[59] VAN DER MAATEN L,HINTON G.Visualizing data using t-sne.[J].Journal of Machine Learning Research,2008,9(86):2579-2605.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发