{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T07:03:26Z","timestamp":1779951806525,"version":"3.53.1"},"reference-count":46,"publisher":"Institution of Engineering and Technology (IET)","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276006"],"award-info":[{"award-number":["62276006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Graph transformers (GTs) with elaborate positional\/structural encodings (PEs\/SEs) have excelled in graph representation learning, especially in graph\u2010level tasks. However, their potential in large\u2010scale node classification remains untapped for several reasons: (i) Current PEs\/SEs are insufficient in modelling large\u2010scale real\u2010world graphs, where a multi\u2010angle portrayal of node properties is required. (ii) The common integration of PEs\/SEs with self\u2010attention overlooks nodes' distinct preferences, leading to sub\u2010optimal performance. (iii) The global receptive field of self\u2010attention leads to quadratic complexity with respect to graph size and introduces potential noise, which significantly hinders the learning of node\u2010level tasks. In this paper, we propose the adaptive node property graph transformer (ANPGT) to address the above issues. ANPGT, with its node property extractor (NPE) and adaptive property integrator (API), flexibly extracts multi\u2010angle node Properties and integrates them according to node\u2010specific preferences. Theoretically, we analyse the necessity of adaptive node property learning. Empirically, ANPGT achieves or matches the best performance on nine real\u2010world datasets (up to three million nodes) and various synthetic benchmarks regarding heterophily and noises. ANPGT exhibits almost linear complexity relative to graph size.<\/jats:p>","DOI":"10.1049\/cit2.70135","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:25:31Z","timestamp":1779949531000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ANPGT: Towards Adaptive Node Property Extraction and Integration"],"prefix":"10.1049","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1808-1585","authenticated-orcid":false,"given":"Qin","family":"Chen","sequence":"first","affiliation":[{"name":"National Key Laboratory of General Artificial, Intelligence, School of Intelligence Science and Technology Peking University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyi","family":"Ren","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial, Intelligence, School of Intelligence Science and Technology Peking University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojie","family":"Song","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial, Intelligence, School of Intelligence Science and Technology Peking University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1145\/3331184.3331267","volume-title":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Wang X.","year":"2019"},{"key":"e_1_2_10_3_1","first-page":"32","volume-title":"Proceedings of the International AAAI Conference on Web and Social Media","author":"Cheng J.","year":"2018"},{"key":"e_1_2_10_4_1","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy A.","year":"2021"},{"key":"e_1_2_10_5_1","first-page":"5997","volume-title":"Conference on Neural Information Processing Systems","author":"Vaswani A.","year":"2017"},{"key":"e_1_2_10_6_1","first-page":"28877","volume-title":"Conference on Neural Information Processing Systems","author":"Ying C.","year":"2021"},{"key":"e_1_2_10_7_1","first-page":"21618","article-title":"Rethinking Graph Transformers With Spectral Attention","volume":"34","author":"Kreuzer D.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_8_1","first-page":"3469","volume-title":"International Conference on Machine Learning","author":"Chen D.","year":"2022"},{"key":"e_1_2_10_9_1","unstructured":"L.Ramp\u00e1\u0161ek M.Galkin V. P.Dwivedi A. T.Luu G.Wolf andD.Beaini \u201cRecipe for a General Powerful Scalable Graph Transformer \u201d preprint arXiv:220512454 (2022)."},{"key":"e_1_2_10_10_1","first-page":"161","volume-title":"ACM International Conference on Information and Knowledge Management","author":"Chen C.","year":"2021"},{"key":"e_1_2_10_11_1","unstructured":"G.Mialon D.Chen M.Selosse andJ.Mairal \u201cGraphiT: Encoding Graph Structure in Transformers \u201d CoRR (2021)."},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1145\/3543507.3583464","volume-title":"Proceedings of the ACM Web Conference 2023","author":"Ma X.","year":"2023"},{"key":"e_1_2_10_13_1","unstructured":"Z.Zhang Q.Liu Q.Hu andC. K.Lee \u201cHierarchical Graph Transformer With Adaptive Node Sampling \u201d preprint arXiv:221003930 (2022)."},{"key":"e_1_2_10_14_1","first-page":"27387","article-title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","volume":"35","author":"Wu Q.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_15_1","volume-title":"International Conference on Learning Representations","author":"Kipf T. N.","year":"2017"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.soc.27.1.415"},{"key":"e_1_2_10_17_1","first-page":"7793","volume-title":"Conference on Neural Information Processing Systems","author":"Zhu J.","year":"2020"},{"key":"e_1_2_10_18_1","volume-title":"International Conference on Learning Representations","author":"Chien E.","year":"2021"},{"key":"e_1_2_10_19_1","first-page":"1362","article-title":"Revisiting Heterophily for Graph Neural Networks","volume":"35","author":"Luan S.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_20_1","article-title":"Convolutional Neural Networks on Graphs With Chebyshev Approximation, Revisited","author":"He M.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_21_1","unstructured":"V. P.Dwivedi A. T.Luu T.Laurent Y.Bengio andX.Bresson \u201cGraph Neural Networks With Learnable Structural and Positional Representations \u201d preprint arXiv:211007875 (2021)."},{"key":"e_1_2_10_22_1","doi-asserted-by":"crossref","unstructured":"X.Li J.Ma Z.Wu et\u00a0al. \u201cRethinking Node\u2010Wise Propagation for Large\u2010Scale Graph Learning \u201d preprint arXiv:240206128 (2024).","DOI":"10.1145\/3589334.3645450"},{"key":"e_1_2_10_23_1","first-page":"11960","volume-title":"Conference on Neural Information Processing Systems","author":"Yun S.","year":"2019"},{"key":"e_1_2_10_24_1","unstructured":"G.Mialon D.Chen M.Selosse andJ.Mairal \u201cGraphit: Encoding Graph Structure in Transformers \u201d preprint arXiv:210605667 (2021)."},{"key":"e_1_2_10_25_1","article-title":"How Expressive Are Transformers in Spectral Domain for Graphs?","author":"Bastos A.","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_2_10_26_1","volume-title":"AAAI Workshop on Deep Learning on Graphs: Methods and Applications","author":"Dwivedi V. P.","year":"2021"},{"key":"e_1_2_10_27_1","volume-title":"International Conference on Learning Representations","author":"Bo D.","year":"2023"},{"key":"e_1_2_10_28_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Fu D.","year":"2024"},{"key":"e_1_2_10_29_1","first-page":"64753","article-title":"Sgformer: Simplifying and Empowering Transformers for large\u2010graph Representations","volume":"36","author":"Wu Q.","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_30_1","first-page":"17375","volume-title":"International Conference on Machine Learning","author":"Kong K.","year":"2023"},{"key":"e_1_2_10_31_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen J.","year":"2022"},{"key":"e_1_2_10_32_1","first-page":"3089","volume-title":"International Joint Conference on Artificial Intelligence","author":"Wang G.","year":"2021"},{"key":"e_1_2_10_33_1","first-page":"4776","volume-title":"Advances in Neural Information Processing Systems","author":"Feng J.","year":"2022"},{"key":"e_1_2_10_34_1","first-page":"1270","volume-title":"Proceedings of the ACM Web Conference","author":"Ma X.","year":"2022"},{"key":"e_1_2_10_35_1","article-title":"A Fuzzy k\u2010Nearest Neighbor Algorithm","author":"Keller J. M.","year":"1985","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"e_1_2_10_36_1","first-page":"22326","article-title":"Long Range Graph Benchmark","volume":"35","author":"Dwivedi V. P.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_37_1","doi-asserted-by":"crossref","DOI":"10.1038\/srep01969","article-title":"Towards Designing Robust Coupled Networks","author":"Schneider C. M.","year":"2013","journal-title":"Scientific Reports"},{"key":"e_1_2_10_38_1","volume-title":"31st International Conference on Distributed Computing Systems Workshops","author":"Wang T.","year":"2011"},{"key":"e_1_2_10_39_1","first-page":"9099","volume-title":"International Conference on Machine Learning","author":"Hua W.","year":"2022"},{"key":"e_1_2_10_40_1","unstructured":"W.Kuang Z.Wang Y.Li Z.Wei andB.Ding \u201cCoarformer: Transformer for Large Graph via Graph Coarsening \u201d (2022)."},{"key":"e_1_2_10_41_1","first-page":"6487","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Wagstaff E.","year":"2019"},{"key":"e_1_2_10_42_1","first-page":"19746","volume-title":"Advances in Neural Information Processing Systems","author":"Buterez D.","year":"2022"},{"key":"e_1_2_10_43_1","first-page":"903","volume-title":"International Conference on Machine Learning","author":"Zadrozny B.","year":"2004"},{"key":"e_1_2_10_44_1","volume-title":"International Conference on Learning Representations","author":"Pei H.","year":"2020"},{"key":"e_1_2_10_45_1","first-page":"20887","article-title":"Large Scale Learning on Non\u2010Homophilous Graphs: New Benchmarks and Strong Simple Methods","volume":"34","author":"Lim D.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_46_1","volume-title":"International Conference on Machine Learning","author":"Yang Z.","year":"2016"},{"key":"e_1_2_10_47_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Veli\u010dkovi\u0107 P.","year":"2018"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70135","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.70135","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:25:41Z","timestamp":1779949541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.70135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":46,"alternative-id":["10.1049\/cit2.70135"],"URL":"https:\/\/doi.org\/10.1049\/cit2.70135","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]},"assertion":[{"value":"2024-08-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"cit2.70135"}}