{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:48:19Z","timestamp":1791686899429,"version":"4.3.4"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109447","type":"journal-article","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T22:07:38Z","timestamp":1785708458000},"page":"109447","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["TriP: A triple-prompt framework aligning pre-training and class-incremental objectives in continual graph learning"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7975-1512","authenticated-orcid":false,"given":"Can-Ming","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Yu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-6847","authenticated-orcid":false,"given":"Pei-Yuan","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5972-559X","authenticated-orcid":false,"given":"Chang-Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109447_bib0001","series-title":"Proceedings of the 30th ACM international conference on information & knowledge management","first-page":"2832","article-title":"Structure aware experience replay for incremental learning in graph-based recommender systems","author":"Ahrabian","year":"2021"},{"key":"10.1016\/j.neunet.2026.109447_bib0002","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"139","article-title":"Memory aware synapses: Learning what (not) to forget","author":"Aljundi","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2026.109447_bib0003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3483595","article-title":"A survey on embedding dynamic graphs","volume":"55","author":"Barros","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.1016\/j.neunet.2026.109447_bib0004","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.neunet.2020.12.003","article-title":"A comprehensive study of class incremental learning algorithms for visual tasks","volume":"135","author":"Belouadah","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109447_bib0005","series-title":"Proceedings of the ACM web conference 2022","first-page":"1292","article-title":"Multimodal continual graph learning with neural architecture search","author":"Cai","year":"2022"},{"key":"10.1016\/j.neunet.2026.109447_bib0006","article-title":"A systematic literature review of spatio-temporal graph neural network models for time series forecasting and classification","volume":"195","author":"Corradini","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109447_bib0007","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4217","article-title":"Lifelong embedding learning and transfer for growing knowledge graphs","volume":"Vol. 37","author":"Cui","year":"2023"},{"issue":"2","key":"10.1016\/j.neunet.2026.109447_bib0008","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1109\/LRA.2021.3056071","article-title":"Continual learning of knowledge graph embeddings","volume":"6","author":"Daruna","year":"2021","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109447_bib0009","doi-asserted-by":"crossref","first-page":"52464","DOI":"10.52202\/075280-2285","article-title":"Universal prompt tuning for graph neural networks","volume":"36","author":"Fang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.neunet.2026.109447_bib0010","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MCI.2022.3222049","article-title":"Graph lifelong learning: A survey","volume":"18","author":"Febrinanto","year":"2023","journal-title":"IEEE Computational Intelligence Magazine"},{"key":"10.1016\/j.neunet.2026.109447_bib0011","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.neunet.2023.04.022","article-title":"Lifelong learning on evolving graphs under the constraints of imbalanced classes and new classes","volume":"164","author":"Galke","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109447_bib0012","series-title":"Joint european conference on machine learning and knowledge discovery in databases","first-page":"423","article-title":"PSP: Pre-training and structure prompt tuning for graph neural networks","author":"Ge","year":"2024"},{"key":"10.1016\/j.neunet.2026.109447_bib0013","series-title":"Joint european conference on machine learning and knowledge discovery in databases","first-page":"197","article-title":"Self-pro: A self-prompt and tuning framework for graph neural networks","author":"Gong","year":"2024"},{"issue":"3","key":"10.1016\/j.neunet.2026.109447_bib0014","first-page":"52","article-title":"Representation learning on graphs: Methods and applications","volume":"40","author":"Hamilton","year":"2017","journal-title":"IEEE Data Engineering Bulletin"},{"key":"10.1016\/j.neunet.2026.109447_bib0015","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109447_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106207","article-title":"A comprehensive survey on deep graph representation learning","volume":"173","author":"Ju","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109447_bib0017","series-title":"5th international conference on learning representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, conference track proceedings","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"issue":"13","key":"10.1016\/j.neunet.2026.109447_bib0018","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2026.109447_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106595","article-title":"MIGP: Metapath integrated graph prompt neural network","volume":"179","author":"Lai","year":"2024","journal-title":"Neural Networks"},{"issue":"12","key":"10.1016\/j.neunet.2026.109447_bib0020","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109447_bib0021","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8653","article-title":"Overcoming catastrophic forgetting in graph neural networks","volume":"Vol. 35","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109447_bib0022","unstructured":"Liu, J., & Zhang, X. (2026). TAAM: Inductive graph-class incremental learning with task-aware adaptive modulation. arXiv: 2602.08036."},{"issue":"9","key":"10.1016\/j.neunet.2026.109447_bib0023","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.109447_bib0024","series-title":"2023 IEEE International conference on data mining (ICDM)","first-page":"1157","article-title":"Cat: Balanced continual graph learning with graph condensation","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109447_bib0025","series-title":"Proceedings of the ACM web conference 2023","first-page":"417","article-title":"GraphPrompt: Unifying pre-training and downstream tasks for graph neural networks","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109447_bib0026","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume":"30","author":"Lopez-Paz","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.neunet.2026.109447_bib0027","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1023\/A:1009953814988","article-title":"Automating the construction of internet portals with machine learning","volume":"3","author":"McCallum","year":"2000","journal-title":"Information Retrieval"},{"key":"10.1016\/j.neunet.2026.109447_bib0028","series-title":"ECAI 2024-27th european conference on artificial intelligence, including 13th conference on prestigious applications of intelligent systems, pais 2024, proceedings","first-page":"1808","article-title":"Graph continual learning with debiased lossless memory replay","author":"Niu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109447_bib0029","doi-asserted-by":"crossref","first-page":"87978","DOI":"10.52202\/079017-2793","article-title":"Replay-and-forget-free graph class-incremental learning: A task profiling and prompting approach","volume":"37","author":"Niu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109447_bib0030","unstructured":"van den Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. CoRR abs\/1807.03748."},{"key":"10.1016\/j.neunet.2026.109447_bib0031","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","article-title":"Continual lifelong learning with neural networks: A review","volume":"113","author":"Parisi","year":"2019","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109447_bib0032","series-title":"Proceedings of the 31st ACM international conference on information & knowledge management","first-page":"1666","article-title":"Reinforced continual learning for graphs","author":"Rakaraddi","year":"2022"},{"key":"10.1016\/j.neunet.2026.109447_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4633","article-title":"Self-supervised continual graph learning in adaptive riemannian spaces","volume":"Vol. 37","author":"Sun","year":"2023"},{"key":"10.1016\/j.neunet.2026.109447_bib0034","series-title":"Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"1717","article-title":"GPPT: Graph pre-training and prompt tuning to generalize graph neural networks","author":"Sun","year":"2022"},{"key":"10.1016\/j.neunet.2026.109447_bib0035","series-title":"Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"2120","article-title":"All in one: Multi-task prompting for graph neural networks","author":"Sun","year":"2023"},{"key":"10.1016\/j.neunet.2026.109447_bib0036","unstructured":"Sun, X., Zhang, J., Wu, X., Cheng, H., Xiong, Y., & Li, J. (2023c). Graph prompt learning: A comprehensive survey and beyond. 10.48550\/ARXIV.2311.16534."},{"key":"10.1016\/j.neunet.2026.109447_bib0037","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.neunet.2023.10.039","article-title":"A survey on few-shot class-incremental learning","volume":"169","author":"Tian","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109447_bib0038","unstructured":"Wang, Q., Sun, X., & Cheng, H. (2024a). Does graph prompt work? A data operation perspective with theoretical analysis. 10.48550\/ARXIV.2410.01635."},{"key":"10.1016\/j.neunet.2026.109447_bib0039","unstructured":"Wang, Q., Zhou, T., Yuan, Y., & Mao, R. (2025a). Prompt-driven continual graph learning. 10.48550\/ARXIV.2502.06327."},{"key":"10.1016\/j.neunet.2026.109447_bib0040","series-title":"Proceedings of the 33rd ACM international conference on information and knowledge management","first-page":"2431","article-title":"DDIPrompt: Drug-drug interaction event prediction based on graph prompt learning","author":"Wang","year":"2024"},{"issue":"3","key":"10.1016\/j.neunet.2026.109447_bib0041","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/TPAMI.2024.3498346","article-title":"A comprehensive survey of forgetting in deep learning beyond continual learning","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109447_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"139","article-title":"Learning to prompt for continual learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109447_bib0043","series-title":"International conference on database systems for advanced applications","first-page":"739","article-title":"IncreGNN: Incremental graph neural network learning by considering node and parameter importance","author":"Wei","year":"2022"},{"key":"10.1016\/j.neunet.2026.109447_bib0044","series-title":"International conference on machine learning","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109447_bib0045","unstructured":"Wu, X., Zhou, K., Sun, M., Wang, X., & Liu, N. (2023). A survey of graph prompting methods: Techniques, applications, and challenges. 10.48550\/ARXIV.2303.07275."},{"key":"10.1016\/j.neunet.2026.109447_bib0046","article-title":"Continual learning: A systematic literature review","author":"Yang","year":"2025","journal-title":"Neural Networks"},{"issue":"2","key":"10.1016\/j.neunet.2026.109447_bib0047","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3618298","article-title":"Contrastive graph prompt-tuning for cross-domain recommendation","volume":"42","author":"Yi","year":"2023","journal-title":"ACM Transactions on Information Systems"},{"key":"10.1016\/j.neunet.2026.109447_bib0048","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"16578","article-title":"HGPROMPT: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning","volume":"Vol. 38","author":"Yu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109447_bib0049","series-title":"Proceedings of the 31st ACM SIGKDD conference on knowledge discovery and data mining v. 2","first-page":"3669","article-title":"GCOT: Chain-of-thought prompt learning for graphs","author":"Yu","year":"2025"},{"key":"10.1016\/j.neunet.2026.109447_bib0050","unstructured":"Yuan, Q., Guan, S., Ni, P., Luo, T., Man, K. L., Wong, P. W. H., & Chang, V. (2023). Continual graph learning: A survey. 10.48550\/ARXIV.2301.12230."},{"key":"10.1016\/j.neunet.2026.109447_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113704","article-title":"MIP: Mutual information-guided prompt for class-incremental continual graph learning","volume":"179","author":"Yuan","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109447_bib0052","series-title":"Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval","first-page":"601","article-title":"Continual learning on dynamic graphs via parameter isolation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109447_bib0053","doi-asserted-by":"crossref","first-page":"13006","DOI":"10.52202\/068431-0945","article-title":"CGLB: Benchmark tasks for continual graph learning","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.neunet.2026.109447_bib0054","doi-asserted-by":"crossref","first-page":"4622","DOI":"10.1109\/TPAMI.2022.3186909","article-title":"Hierarchical prototype networks for continual graph representation learning","volume":"45","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109447_bib0055","series-title":"2022 IEEE International conference on data mining (ICDM)","first-page":"1335","article-title":"Sparsified subgraph memory for continual graph representation learning","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109447_bib0056","unstructured":"Zhang, X., Song, D., & Tao, D. (2024). Continual learning on graphs: Challenges, solutions, and opportunities. 10.48550\/ARXIV.2402.11565."},{"issue":"3","key":"10.1016\/j.neunet.2026.109447_bib0057","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1007\/s11263-024-02218-0","article-title":"Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need","volume":"133","author":"Zhou","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109447_bib0058","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23554","article-title":"Expandable subspace ensemble for pre-trained model-based class-incremental learning","author":"Zhou","year":"2024"},{"key":"10.1016\/j.neunet.2026.109447_bib0059","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4714","article-title":"Overcoming catastrophic forgetting in graph neural networks with experience replay","volume":"Vol. 35","author":"Zhou","year":"2021"},{"issue":"9","key":"10.1016\/j.neunet.2026.109447_bib0060","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109447_bib0061","unstructured":"Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., & Wang, L. (2020a). Deep graph contrastive representation learning. CoRR abs\/2006.04131."},{"key":"10.1016\/j.neunet.2026.109447_bib0062","series-title":"ICML workshop on graph representation learning and beyond","article-title":"Deep graph contrastive representation learning","author":"Zhu","year":"2020"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009056?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009056?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:33:38Z","timestamp":1791686018000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026009056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":62,"alternative-id":["S0893608026009056"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109447","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TriP: A triple-prompt framework aligning pre-training and class-incremental objectives in continual graph learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109447","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109447"}}