{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:06:35Z","timestamp":1788879995476,"version":"build-2803163510"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62306322, U25B2047, 62272469"],"award-info":[{"award-number":["62306322, U25B2047, 62272469"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Science and Technology Innovation Program of Hunan Province","award":["2023RC1007"],"award-info":[{"award-number":["2023RC1007"]}]},{"DOI":"10.13039\/501100003246","name":"Dutch Research Council","doi-asserted-by":"crossref","award":["024.004.022, NWA.1389.20.183, and KICH3.LTP.20.006"],"award-info":[{"award-number":["024.004.022, NWA.1389.20.183, and KICH3.LTP.20.006"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["101201510 (UNITE)"],"award-info":[{"award-number":["101201510 (UNITE)"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>\n                    Heterogeneous information networks (HINs) play an indispensable role in a wide range of domain-specific applications, from recommender systems to conversational platforms. Textual HINs are graphs with abundant textual information. Currently, most advanced approaches to mine textual features from HINs follow a \u201cpre-training and fine-tuning\u201d schema, which may cause a \u201cnegative transfer\u201d problem since there is a gap between pre-training tasks and downstream tasks. We propose a prompt-learning framework\n                    <jats:sans-serif>P-HIN<\/jats:sans-serif>\n                    that provides a new angle to align textual information and graph information, while narrowing down the gap between the pre-trained models and various downstream tasks. To the best of our knowledge, we are among the first to introduce and exploit the idea of prompt learning to align HIN features and textual features. The proposed framework\n                    <jats:sans-serif>P-HIN<\/jats:sans-serif>\n                    is composed of a text encoder and a graph encoder and uses contrastive learning to align and fuse the graph\u2013text pair. This pre-training operation naturally fits the few-shot learning setting. For the graph encoder, we introduce two graph pre-training tasks, masked node modeling and edge reconstruction, to exploit self-supervised information. During optimization, instead of handcrafted prompts, we use a learnable continuous text that enables more efficient and task-relevant transfer to downstream datasets. We consider a residual connection to use the context from the graph to prompt the text encoder. In experiments,\n                    <jats:sans-serif>P-HIN<\/jats:sans-serif>\n                    consistently and significantly outperforms state-of-the-art alternatives on all real-life datasets.\n                  <\/jats:p>","DOI":"10.1145\/3831697","type":"journal-article","created":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T19:56:35Z","timestamp":1785614195000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt Learning for Textual Heterogeneous Information Networks"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3565-2482","authenticated-orcid":false,"given":"Yang","family":"Fang","sequence":"first","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6339-0219","authenticated-orcid":false,"given":"Xiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3552-0685","authenticated-orcid":false,"given":"Daojian","family":"Zeng","sequence":"additional","affiliation":[{"name":"Hunan Normal University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6957-3769","authenticated-orcid":false,"given":"Weidong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten de","family":"Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-7860","authenticated-orcid":false,"given":"Minnan","family":"Luo","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University, Xi\u2019an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9066-1475","authenticated-orcid":false,"given":"Xinwang","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1086\/228631"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.021"},{"key":"e_1_3_2_5_2","first-page":"7562","volume-title":"AAAI","author":"Cheng Pengyu","year":"2020","unstructured":"Pengyu Cheng, Yitong Li, Xinyuan Zhang, Liqun Chen, David E. Carlson, and Lawrence Carin. 2020. Dynamic embedding on textual networks via a Gaussian process. In AAAI. AAAI Press, 7562\u20137569."},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1145\/3289600.3290964","volume-title":"WSDM","author":"Ding Kaize","year":"2019","unstructured":"Kaize Ding, Jundong Li, and Huan Liu. 2019. Interactive anomaly detection on attributed networks. In WSDM. ACM, 357\u2013365."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098036"},{"key":"e_1_3_2_8_2","volume-title":"NeurIPS","author":"Fang Taoran","year":"2023","unstructured":"Taoran Fang, Yunchao Zhang, Yang Yang, Chunping Wang, and Lei Chen. 2023. Universal prompt tuning for graph neural networks. In NeurIPS."},{"issue":"8","key":"e_1_3_2_9_2","first-page":"8372","article-title":"PF-HIN:Pre-training for heterogeneous information networks","volume":"35","author":"Fang Yang","year":"2023","unstructured":"Yang Fang, Xiang Zhao, Yifan Chen, Weidong Xiao, and Maarten de Rijke. 2023. PF-HIN:Pre-training for heterogeneous information networks. IEEE Transactions on Knowledge and Data Engineering 35, 8 (2023), 8372\u20138385.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_10_2","first-page":"913","volume-title":"SIGIR","author":"Fang Yang","year":"2019","unstructured":"Yang Fang, Xiang Zhao, Peixin Huang, Weidong Xiao, and Maarten de Rijke. 2019. M-HIN: Complex embeddings for heterogeneous information networks via metagraphs. In SIGIR, 913\u2013916."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485189"},{"key":"e_1_3_2_12_2","first-page":"1797","volume-title":"CIKM","author":"Fu Tao-Yang","year":"2017","unstructured":"Tao-Yang Fu, Wang-Chien Lee, and Zhen Lei. 2017. HIN2Vec: Explore meta-paths in heterogeneous information networks for representation learning. In CIKM, 1797\u20131806."},{"key":"e_1_3_2_13_2","volume-title":"ICLR","author":"Fu Xingbo","year":"2025","unstructured":"Xingbo Fu, Yinhan He, and Jundong Li. 2025. Edge prompt tuning for graph neural networks. In ICLR. OpenReview.net."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Maarten Grootendorst. 2020. KeyBERT: Minimal keyword extraction with BERT. Zenodo. Retrieved from 10.5281\/zenodo.4461265","DOI":"10.5281\/zenodo.4461265"},{"key":"e_1_3_2_15_2","unstructured":"Qingyu Guo Fuzhen Zhuang Chuan Qin Hengshu Zhu Xing Xie Hui Xiong and Qing He. 2020. A survey on knowledge graph-based recommender systems. arXiv:2003.00911. Retrieved from https:\/\/arxiv.org\/abs\/2003.00911"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"e_1_3_2_17_2","unstructured":"Zhipeng Huang and Nikos Mamoulis. 2017. Heterogeneous information network embedding for meta path based proximity. arXiv:1701.05291. Retrieved from https:\/\/arxiv.org\/abs\/1701.05291"},{"key":"e_1_3_2_18_2","first-page":"756","volume-title":"KDD","author":"Jiang Xunqiang","year":"2021","unstructured":"Xunqiang Jiang, Tianrui Jia, Yuan Fang, Chuan Shi, Zhe Lin, and Hui Wang. 2021. Pre-training on large-scale heterogeneous graph. In KDD. ACM, 756\u2013766."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482332"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"e_1_3_2_21_2","first-page":"7005","volume-title":"ACL","author":"Jin Bowen","year":"2023","unstructured":"Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng, Xinyang Zhang, Qi Zhu, and Jiawei Han. 2023. Patton: Language model pretraining on text-rich networks. In ACL. Association for Computational Linguistics, 7005\u20137020."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472956"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_24_2","first-page":"1","volume-title":"Transactions on Machine Learning Research","author":"Li Jiazheng","year":"2025","unstructured":"Jiazheng Li, Jundong Li, and Chuxu Zhang. 2025. Instance-aware graph prompt learning. Transactions on Machine Learning Research 25, 2 (2025), 1\u201320."},{"key":"e_1_3_2_25_2","first-page":"912","volume-title":"ICDE","author":"Li Xiang","year":"2021","unstructured":"Xiang Li, Danhao Ding, Ben Kao, Yizhou Sun, and Nikos Mamoulis. 2021. Leveraging meta-path contexts for classification in heterogeneous information networks. In ICDE. IEEE, 912\u2013923."},{"key":"e_1_3_2_26_2","first-page":"4582","volume-title":"ACL\/IJCNLP","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. In ACL\/IJCNLP, 4582\u20134597."},{"key":"e_1_3_2_27_2","first-page":"1259","volume-title":"SIGIR","author":"Lin Jianghao","year":"2021","unstructured":"Jianghao Lin, Weiwen Liu, Xinyi Dai, Weinan Zhang, Shuai Li, Ruiming Tang, Xiuqiang He, Jianye Hao, and Yong Yu. 2021. A graph-enhanced click model for web search. In SIGIR. ACM, 1259\u20131268."},{"key":"e_1_3_2_28_2","unstructured":"Pengfei Liu Weizhe Yuan Jinlan Fu Zhengbao Jiang Hiroaki Hayashi and Graham Neubig. 2021. Pre-train prompt and predict: A systematic survey of prompting methods in natural language processing. arXiv:2107.13586. Retrieved from https:\/\/arxiv.org\/abs\/2107.13586"},{"key":"e_1_3_2_29_2","first-page":"417","volume-title":"WWW","author":"Liu Zemin","year":"2023","unstructured":"Zemin Liu, Xingtong Yu, Yuan Fang, and Xinming Zhang. 2023. GraphPrompt: Unifying pre-training and downstream tasks for graph neural networks. In WWW. ACM, 417\u2013428."},{"key":"e_1_3_2_30_2","first-page":"1015","volume-title":"WWW","author":"Ma Yihong","year":"2024","unstructured":"Yihong Ma, Ning Yan, Jiayu Li, Masood S. Mortazavi, and Nitesh V. Chawla. 2024. HetGPT: Harnessing the power of prompt tuning in pre-trained heterogeneous graph neural networks. In WWW. ACM, 1015\u20131023."},{"key":"e_1_3_2_31_2","first-page":"8748","volume-title":"ICML","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In ICML, Vol. 139. PMLR, 8748\u20138763."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000063"},{"key":"e_1_3_2_34_2","first-page":"1829","volume-title":"EMNLP","author":"Shen Dinghan","year":"2018","unstructured":"Dinghan Shen, Xinyuan Zhang, Ricardo Henao, and Lawrence Carin. 2018. Improved semantic-aware network embedding with fine-grained word alignment. In EMNLP. Association for Computational Linguistics, 1829\u20131838."},{"key":"e_1_3_2_35_2","first-page":"1717","volume-title":"KDD","author":"Sun Mingchen","year":"2022","unstructured":"Mingchen Sun, Kaixiong Zhou, Xin He, Ying Wang, and Xin Wang. 2022. GPPT: Graph pre-training and prompt tuning to generalize graph neural networks. In KDD. ACM, 1717\u20131727."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599256"},{"key":"e_1_3_2_37_2","unstructured":"Xiaofei Sun Jiang Guo Xiao Ding and Ting Liu. 2016. A general framework for content-enhanced network representation learning. arXiv:1610.02906. Retrieved from https:\/\/arxiv.org\/abs\/1610.02906"},{"key":"e_1_3_2_38_2","unstructured":"Xiangguo Sun Jiawen Zhang Xixi Wu Hong Cheng Yun Xiong and Jia Li. 2023. Graph prompt learning: A comprehensive survey and beyond. arXiv:2311.16534. Retrieved from https:\/\/arxiv.org\/abs\/2311.16534"},{"issue":"2","key":"e_1_3_2_39_2","first-page":"20","article-title":"Mining heterogeneous information networks: A structural analysis approach","volume":"14","author":"Sun Yizhou","year":"2012","unstructured":"Yizhou Sun and Jiawei Han. 2012. Mining heterogeneous information networks: A structural analysis approach. ACM SIGKDD Explorations Newsletter 14, 2 (2012), 20\u201328.","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"e_1_3_2_40_2","first-page":"1722","volume-title":"ACL","author":"Tu Cunchao","year":"2017","unstructured":"Cunchao Tu, Han Liu, Zhiyuan Liu, and Maosong Sun. 2017. CANE: Context-aware network embedding for relation modeling. In ACL. Association for Computational Linguistics, 1722\u20131731."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939753"},{"key":"e_1_3_2_42_2","volume-title":"ICML","volume":"267","author":"Wang Qunzhong","year":"2025","unstructured":"Qunzhong Wang, Xiangguo Sun, and Hong Cheng. 2025. Does graph prompt work? A data operation perspective with theoretical analysis. In ICML, Vol. 267. PMLR\/OpenReview.net."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467415"},{"key":"e_1_3_2_44_2","first-page":"4697","volume-title":"EMNLP-IJCNLP","author":"Xu Zenan","year":"2019","unstructured":"Zenan Xu, Qinliang Su, Xiaojun Quan, and Weijia Zhang. 2019. A deep neural information fusion architecture for textual network embeddings. In EMNLP-IJCNLP. Association for Computational Linguistics, 4697\u20134705."},{"key":"e_1_3_2_45_2","first-page":"2111","volume-title":"IJCAI","author":"Yang Cheng","year":"2015","unstructured":"Cheng Yang, Zhiyuan Liu, Deli Zhao, Maosong Sun, and Edward Y. Chang. 2015. Network representation learning with rich text information. In IJCAI. AAAI Press, 2111\u20132117."},{"key":"e_1_3_2_46_2","first-page":"10816","volume-title":"AAAI","author":"Yang Xiaocheng","year":"2023","unstructured":"Xiaocheng Yang, Mingyu Yan, Shirui Pan, Xiaochun Ye, and Dongrui Fan. 2023. Simple and efficient heterogeneous graph neural network. In AAAI. AAAI Press, 10816\u201310824."},{"issue":"2","key":"e_1_3_2_47_2","first-page":"1637","article-title":"Interpretable and efficient heterogeneous graph convolutional network","volume":"35","author":"Yang Yaming","year":"2023","unstructured":"Yaming Yang, Ziyu Guan, Jianxin Li, Wei Zhao, Jiangtao Cui, and Quan Wang. 2023. Interpretable and efficient heterogeneous graph convolutional network. IEEE Transactions on Knowledge and Data Engineering 35, 2 (2023), 1637\u20131650.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_48_2","volume-title":"NeurIPS","author":"Yang Yaming","year":"2022","unstructured":"Yaming Yang, Ziyu Guan, Zhe Wang, Wei Zhao, Cai Xu, Weigang Lu, and Jianbin Huang. 2022. Self-supervised heterogeneous graph pre-training based on structural clustering. In NeurIPS."},{"key":"e_1_3_2_49_2","volume-title":"NeurIPS","author":"Yasunaga Michihiro","year":"2022","unstructured":"Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D. Manning, Percy Liang, and Jure Leskovec. 2022. Deep bidirectional language-knowledge graph pretraining. In NeurIPS."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.04.004"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"e_1_3_2_53_2","unstructured":"Kaiyang Zhou Jingkang Yang Chen Change Loy and Ziwei Liu. 2021. Learning to prompt for vision-language models. arXiv:2109.01134. Retrieved from https:\/\/arxiv.org\/abs\/2109.01134"},{"key":"e_1_3_2_54_2","volume-title":"NeurIPS","author":"Zi Chenyi","year":"2024","unstructured":"Chenyi Zi, Haihong Zhao, Xiangguo Sun, Yiqing Lin, Hong Cheng, and Jia Li. 2024. ProG: A graph prompt learning benchmark. In NeurIPS."}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3831697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:07:06Z","timestamp":1788876426000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3831697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":53,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1145\/3831697"],"URL":"https:\/\/doi.org\/10.1145\/3831697","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"assertion":[{"value":"2025-10-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}