{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T23:29:17Z","timestamp":1773098957471,"version":"3.50.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s10489-025-06754-1","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:46:54Z","timestamp":1752140814000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-modal parameter-efficient fine-tuning via graph neural network"],"prefix":"10.1007","volume":"55","author":[{"given":"Bin","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3566-3050","authenticated-orcid":false,"given":"Jiaxuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,9]]},"reference":[{"key":"6754_CR1","doi-asserted-by":"crossref","unstructured":"Vu T, Lester B, Constant N, Al-Rfou R, Cer D (2021) Spot: Better frozen model adaptation through soft prompt transfer. arXiv:2110.07904","DOI":"10.18653\/v1\/2022.acl-long.346"},{"key":"6754_CR2","doi-asserted-by":"crossref","unstructured":"Lu J, Yan F, Zhang X, Gao Y, Zhang S (2024) Pathotune: Adapting visual foundation model to pathological specialists. arXiv:2403.16497","DOI":"10.1007\/978-3-031-72083-3_37"},{"key":"6754_CR3","doi-asserted-by":"crossref","unstructured":"Li XL, Liang P (2021) Prefix-tuning: Optimizing continuous prompts for generation. arXiv:2101.00190","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"6754_CR4","unstructured":"Houlsby N, Giurgiu A, Jastrzebski S, Morrone B, De\u00a0Laroussilhe Q, Gesmundo A, Attariyan M, Gelly S (2019) Parameter-efficient transfer learning for nlp. In: International Conference on Machine Learning, pp 2790\u20132799. PMLR"},{"key":"6754_CR5","first-page":"16664","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen S, Ge C, Tong Z, Wang J, Song Y, Wang J, Luo P (2022) Adaptformer: Adapting vision transformers for scalable visual recognition. Adv Neural Inf Process Syst 35:16664\u201316678","journal-title":"Adv Neural Inf Process Syst"},{"issue":"9","key":"6754_CR6","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou K, Yang J, Loy CC, Liu Z (2022) Learning to prompt for vision-language models. Int J Comput Vis 130(9):2337\u20132348","journal-title":"Int J Comput Vis"},{"key":"6754_CR7","unstructured":"Zhang R, Fang R, Zhang W, Gao P, Li K, Dai J, Qiao Y, Li H (2021) Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv:2111.03930"},{"key":"6754_CR8","first-page":"52464","volume":"36","author":"T Fang","year":"2023","unstructured":"Fang T, Zhang Y, Yang Y, Wang C, Chen L (2023) Universal prompt tuning for graph neural networks. Adv Neural Inf Process Syst 36:52464\u201352489","journal-title":"Adv Neural Inf Process Syst"},{"key":"6754_CR9","doi-asserted-by":"crossref","unstructured":"Liu Z, Yu X, Fang Y, Zhang X (2023) Graphprompt: Unifying pre-training and downstream tasks for graph neural networks. In: Proceedings of the ACM Web Conference 2023, pp 417\u2013428","DOI":"10.1145\/3543507.3583386"},{"key":"6754_CR10","unstructured":"Aich A (2021) Elastic weight consolidation (ewc): Nuts and bolts. arXiv:2105.04093"},{"key":"6754_CR11","unstructured":"Wan Y, Wang W, Zou G, Zhang B (2024) Cross-modal feature alignment and fusion for composed image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8384\u20138388"},{"key":"6754_CR12","doi-asserted-by":"crossref","unstructured":"Liao B, Meng Y, Monz C (2023) Parameter-efficient fine-tuning without introducing new latency. arXiv:2305.16742","DOI":"10.18653\/v1\/2023.acl-long.233"},{"key":"6754_CR13","doi-asserted-by":"crossref","unstructured":"Li J, Aitken W, Bhambhoria R, Zhu X (2023) Prefix propagation: Parameter-efficient tuning for long sequences. arXiv:2305.12086","DOI":"10.18653\/v1\/2023.acl-short.120"},{"key":"6754_CR14","doi-asserted-by":"crossref","unstructured":"Gheini M, Ma X, May J (2022) Know where you\u2019re going: Meta-learning for parameter-efficient fine-tuning. arXiv:2205.12453","DOI":"10.18653\/v1\/2023.findings-acl.737"},{"key":"6754_CR15","doi-asserted-by":"crossref","unstructured":"Pouramini A, Faili H (2024) Matching tasks to objectives: Fine-tuning and prompt-tuning strategies for encoder-decoder pre-trained language models. Appl Intell, 1\u201328","DOI":"10.1007\/s10489-024-05660-2"},{"key":"6754_CR16","doi-asserted-by":"crossref","unstructured":"Li J, Wang Y, Gao Z, Wei Y (2024) Eftnet: an efficient fine-tuning method for few-shot segmentation. Appl Intell, 1\u201320","DOI":"10.1007\/s10489-024-05582-z"},{"issue":"3","key":"6754_CR17","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","volume":"5","author":"N Ding","year":"2023","unstructured":"Ding N, Qin Y, Yang G, Wei F, Yang Z, Su Y, Hu S, Chen Y, Chan C-M, Chen W et al (2023) Parameter-efficient fine-tuning of large-scale pre-trained language models. Nature Mach Intell 5(3):220\u2013235","journal-title":"Nature Mach Intell"},{"key":"6754_CR18","unstructured":"Zaken EB, Ravfogel S, Goldberg Y (2021) Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv:2106.10199"},{"key":"6754_CR19","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) Lora: Low-rank adaptation of large language models. arXiv:2106.09685"},{"key":"6754_CR20","doi-asserted-by":"crossref","unstructured":"Dutta A, Alcaraz J, TehraniJamsaz A, Cesar E, Sikora A, Jannesari A (2023) Performance optimization using multimodal modeling and heterogeneous gnn. In: Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing, pp 45\u201357","DOI":"10.1145\/3588195.3592984"},{"key":"6754_CR21","unstructured":"Lialin V, Deshpande V, Rumshisky A (2023) Scaling down to scale up: A guide to parameter-efficient fine-tuning. arXiv:2303.15647"},{"key":"6754_CR22","first-page":"109","volume":"35","author":"D Lian","year":"2022","unstructured":"Lian D, Zhou D, Feng J, Wang X (2022) Scaling & shifting your features: A new baseline for efficient model tuning. Adv Neural Inf Process Syst 35:109\u2013123","journal-title":"Adv Neural Inf Process Syst"},{"key":"6754_CR23","doi-asserted-by":"crossref","unstructured":"Hirano M, Izumi K (2022) Parameter tuning method for multi-agent simulation using reinforcement learning. In: 2022 9th International Conference on Behavioural and Social Computing (BESC), pp 1\u20137. IEEE","DOI":"10.1109\/BESC57393.2022.9995509"},{"key":"6754_CR24","unstructured":"Wang Y, Wu J, Dabral T, Zhang J, Brown G, Lu C-T, Liu F, Liang Y, Pang B, Bendersky M, et al (2023) Non-intrusive adaptation: Input-centric parameter-efficient fine-tuning for versatile multimodal modeling. arXiv:2310.12100"},{"key":"6754_CR25","doi-asserted-by":"crossref","unstructured":"Lu Y, Liu J, Zhang Y, Liu Y, Tian X (2022) Prompt distribution learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5206\u20135215","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"6754_CR26","unstructured":"Lu Y, Li C, Liu H, Yang J, Gao J, Shen Y (2023) An empirical study of scaling instruct-tuned large multimodal models. arXiv:2309.09958"},{"issue":"2","key":"6754_CR27","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao P, Geng S, Zhang R, Ma T, Fang R, Zhang Y, Li H, Qiao Y (2024) Clip-adapter: Better vision-language models with feature adapters. Int J Comput Vis 132(2):581\u2013595","journal-title":"Int J Comput Vis"},{"key":"6754_CR28","doi-asserted-by":"crossref","unstructured":"Zhang R, Zhang W, Fang R, Gao P, Li K, Dai J, Qiao Y, Li H (2022) Tip-adapter: Training-free adaption of clip for few-shot classification. In: European Conference on Computer Vision, pp 493\u2013510. Springer","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"6754_CR29","doi-asserted-by":"crossref","unstructured":"Yu T, Lu Z, Jin X, Chen Z, Wang X (2023) Task residual for tuning vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10899\u201310909","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"6754_CR30","unstructured":"Wu C, Wang T, Ge Y, Lu Z, Zhou R, Shan Y, Luo P (2023) [CDATA[\\pi]]$$\\pi$$-tuning: Transferring multimodal foundation models with optimal multi-task interpolation. In: International Conference on Machine Learning, pp 37713\u201337727. PMLR"},{"key":"6754_CR31","doi-asserted-by":"crossref","unstructured":"Xu B, Xu H, Zhao H, Gao J, Liang D, Li Y, Wang W, Feng Y, Shi G (2023) Source apportionment of fine particulate matter at a megacity in china, using an improved regularization supervised pmf model. Sci Total Environ 879:163198","DOI":"10.1016\/j.scitotenv.2023.163198"},{"issue":"1","key":"6754_CR32","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2008) The graph neural network model. IEEE Trans Neural Netw 20(1):61\u201380","journal-title":"IEEE Trans Neural Netw"},{"key":"6754_CR33","unstructured":"Chen Z, Li X, Bruna J (2017) Supervised community detection with line graph neural networks. arXiv:1705.08415"},{"key":"6754_CR34","doi-asserted-by":"crossref","unstructured":"Schlichtkrull M, Kipf TN, Bloem P, Van Den\u00a0Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, 3\u20137 June, 2018, Proceedings 15, pp 593\u2013607. Springer","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"6754_CR35","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv:1710.10903"},{"key":"6754_CR36","unstructured":"Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Adv Neural Inf Process Syst 30"},{"key":"6754_CR37","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1109\/TIP.2023.3236144","volume":"32","author":"J Lu","year":"2023","unstructured":"Lu J, Wan H, Li P, Zhao X, Ma N, Gao Y (2023) Exploring high-order spatio-temporal correlations from skeleton for person re-identification. IEEE Trans Image Process 32:949\u2013963","journal-title":"IEEE Trans Image Process"},{"key":"6754_CR38","doi-asserted-by":"crossref","unstructured":"Gao Y, Lu J, Li S, Li Y, Du S (2024) Hypergraph-based multi-view action recognition using event cameras. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2024.3382117"},{"key":"6754_CR39","doi-asserted-by":"crossref","unstructured":"Dai Y, Shou L, Gong M, Xia X, Kang Z, Xu Z, Jiang D (2022) Graph fusion network for text classification. Knowl-based Syst 236:107659","DOI":"10.1016\/j.knosys.2021.107659"},{"issue":"6","key":"6754_CR40","doi-asserted-by":"publisher","first-page":"6671","DOI":"10.1007\/s10489-022-03744-5","volume":"53","author":"F Zhang","year":"2023","unstructured":"Zhang F, Li J, Cheng J (2023) Improving entity alignment via attribute and external knowledge filtering. Appl Intell 53(6):6671\u20136681","journal-title":"Appl Intell"},{"key":"6754_CR41","doi-asserted-by":"crossref","unstructured":"Zhu X, Wu Y, Zhang Q, Chen Z, He Y (2023) Dynamic link prediction for new nodes in temporal graph networks. arXiv:2310.09787","DOI":"10.1109\/IJCNN60899.2024.10650904"},{"issue":"23","key":"6754_CR42","doi-asserted-by":"publisher","first-page":"29282","DOI":"10.1007\/s10489-023-05083-5","volume":"53","author":"D Han","year":"2023","unstructured":"Han D, Kim D, Kim M, Han K, Yi MY (2023) Temporal enhanced inductive graph knowledge tracing. Appl Intell 53(23):29282\u201329299","journal-title":"Appl Intell"},{"key":"6754_CR43","doi-asserted-by":"crossref","unstructured":"Meng Z, Chen Z, Tan J, Wang W, Zhang Z, Huang J, Fang J (2022) Regeneration performance and particulate emission characteristics during active regeneration process of gpf with ash loading. Chem Eng Sci 248:117114","DOI":"10.1016\/j.ces.2021.117114"},{"key":"6754_CR44","doi-asserted-by":"crossref","unstructured":"Sun M, Zhou K, He X, Wang Y, Wang X (2022) Gppt: Graph pre-training and prompt tuning to generalize graph neural networks. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp 1717\u20131727","DOI":"10.1145\/3534678.3539249"},{"key":"6754_CR45","unstructured":"Diao C, Zhou K, Liu Z, Huang X, Hu X (2022) Molcpt: Molecule continuous prompt tuning to generalize molecular representation learning. arXiv:2212.10614"},{"key":"6754_CR46","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth 16x16 words: Transform Image Recogn Scale. arXiv:2010.11929"},{"key":"6754_CR47","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6754_CR48","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"key":"6754_CR49","unstructured":"Douze M, Guzhva A, Deng C, Johnson J, Szilvasy G, Mazar\u00e9 P-E, Lomeli M, Hosseini L, J\u00e9gou H (2024) The faiss library. arXiv:2401.08281"},{"issue":"3","key":"6754_CR50","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson J, Douze M, J\u00e9gou H (2019) Billion-scale similarity search with gpus. IEEE Trans Big Data 7(3):535\u2013547","journal-title":"IEEE Trans Big Data"},{"key":"6754_CR51","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907"},{"key":"6754_CR52","doi-asserted-by":"crossref","unstructured":"Parkhi OM, Vedaldi A, Zisserman A, Jawahar C (2012) Cats and dogs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp 3498\u20133505. IEEE","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"6754_CR53","doi-asserted-by":"crossref","unstructured":"Nilsback M-E, Zisserman A (2008) Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp 722\u2013729. IEEE","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"6754_CR54","doi-asserted-by":"crossref","unstructured":"Bossard L, Guillaumin M, Van\u00a0Gool L (2014) Food-101\u2013mining discriminative components with random forests. In: Computer vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, 6-12 September, 2014, Proceedings, Part VI 13, pp 446\u2013461. Springer","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"6754_CR55","doi-asserted-by":"crossref","unstructured":"Lin B, Zhu B, Ye Y, Ning M, Jin P, Yuan L (2023) Video-llava: Learning united visual representation by alignment before projection. arXiv:2311.10122","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"6754_CR56","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: Data, models and evaluation metrics. J Artif Intell Res 47:853\u2013899","journal-title":"J Artif Intell Res"},{"key":"6754_CR57","unstructured":"Li J, Li D, Savarese S, Hoi S (2023) Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp 19730\u201319742. PMLR"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06754-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06754-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06754-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T15:56:41Z","timestamp":1758297401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06754-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,9]]},"references-count":57,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["6754"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06754-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,9]]},"assertion":[{"value":"25 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study did not involve any human or animal subjects, hence ethical approval and consent to participate are not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"We have reviewed the manuscript and consent to its publication.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"858"}}