{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T18:04:14Z","timestamp":1781114654403,"version":"3.54.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113877","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T16:25:11Z","timestamp":1777479911000},"page":"113877","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Aggregation-aware MLP: An unsupervised approach for graph message-passing"],"prefix":"10.1016","volume":"179","author":[{"given":"Xuanting","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erlin","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keren","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4103-0954","authenticated-orcid":false,"given":"Zhao","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113877_b1","unstructured":"M. Welling, T.N. Kipf, Semi-supervised classification with graph convolutional networks, in: J. International Conference on Learning Representations, 2017."},{"key":"10.1016\/j.patcog.2026.113877_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110597","article-title":"A unified framework for convolution-based graph neural networks","volume":"155","author":"Pan","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113877_b3","doi-asserted-by":"crossref","unstructured":"X. Xie, B. Li, E. Pan, Z. Guo, Z. Kang, W. Chen, One node one model: Featuring the missing-half for graph clustering, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 2025, pp. 21688\u201321696.","DOI":"10.1609\/aaai.v39i20.35473"},{"key":"10.1016\/j.patcog.2026.113877_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111307","article-title":"Graph neural network based on graph kernel: A survey","volume":"161","author":"Xu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113877_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119645","article-title":"Contrastive graph clustering with adaptive filter","volume":"219","author":"Xie","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113877_b6","article-title":"Generalizing aggregation functions in GNNs: building high capacity and robust GNNs via nonlinear aggregation","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113877_b7","series-title":"IJCAI","first-page":"2108","article-title":"Raw-gnn: Random walk aggregation based graph neural network","author":"Jin","year":"2022"},{"key":"10.1016\/j.patcog.2026.113877_b8","doi-asserted-by":"crossref","unstructured":"D. He, C. Liang, H. Liu, M. Wen, P. Jiao, Z. Feng, Block modeling-guided graph convolutional neural networks, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, 2022, pp. 4022\u20134029.","DOI":"10.1609\/aaai.v36i4.20319"},{"key":"10.1016\/j.patcog.2026.113877_b9","doi-asserted-by":"crossref","unstructured":"D. Jin, C. Huo, C. Liang, L. Yang, Heterogeneous graph neural network via attribute completion, in: Proceedings of the Web Conference 2021, 2021, pp. 391\u2013400.","DOI":"10.1145\/3442381.3449914"},{"key":"10.1016\/j.patcog.2026.113877_b10","series-title":"International Conference on Machine Learning","article-title":"Finding global homophily in graph neural networks when meeting heterophily","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.113877_b11","unstructured":"E. Chien, J. Peng, P. Li, O. Milenkovic, Adaptive Universal Generalized PageRank Graph Neural Network, in: International Conference on Learning Representations, 2021."},{"issue":"4","key":"10.1016\/j.patcog.2026.113877_b12","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.1109\/TKDE.2020.3002567","article-title":"Fairness in semi-supervised learning: Unlabeled data help to reduce discrimination","volume":"34","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.patcog.2026.113877_b13","article-title":"Multi-channel set polynomial based label regularized graph neural networks against extreme data scarcity","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113877_b14","doi-asserted-by":"crossref","DOI":"10.1109\/TCYB.2026.3671252","article-title":"Provable filter for real-world graph clustering","author":"Xie","year":"2026","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2026.113877_b15","series-title":"2022 IEEE International Conference on Data Mining","first-page":"1287","article-title":"Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks","author":"Yan","year":"2022"},{"key":"10.1016\/j.patcog.2026.113877_b16","first-page":"4694","article-title":"Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks","volume":"35","author":"Lei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"10.1016\/j.patcog.2026.113877_b17","first-page":"13024","article-title":"DeeperGCN: training deeper GCNs with generalized aggregation functions","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113877_b18","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b19","first-page":"2148","article-title":"Multi-view contrastive graph clustering","volume":"34","author":"Pan","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b20","series-title":"International Conference on Machine Learning","first-page":"26868","article-title":"Beyond homophily: Reconstructing structure for graph-agnostic clustering","author":"Pan","year":"2023"},{"key":"10.1016\/j.patcog.2026.113877_b21","doi-asserted-by":"crossref","unstructured":"Z. Liu, C. Zeng, G. Zheng, Graph data condensation via self-expressive graph structure reconstruction, in: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024, pp. 1992\u20132002.","DOI":"10.1145\/3637528.3671710"},{"key":"10.1016\/j.patcog.2026.113877_b22","doi-asserted-by":"crossref","unstructured":"G. Li, M. Muller, A. Thabet, B. Ghanem, DeepGCNs: Can GCNs go as deep as CNNs?, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9267\u20139276.","DOI":"10.1109\/ICCV.2019.00936"},{"key":"10.1016\/j.patcog.2026.113877_b23","series-title":"The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"439","article-title":"CAST: a correlation-based adaptive spectralacm clustering algorithm on multi-scale data","author":"Li","year":"2020"},{"issue":"7","key":"10.1016\/j.patcog.2026.113877_b24","doi-asserted-by":"crossref","first-page":"13177","DOI":"10.1109\/TNNLS.2024.3473618","article-title":"CDC: A simple framework for complex data clustering","volume":"36","author":"Kang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"10.1016\/j.patcog.2026.113877_b25","doi-asserted-by":"crossref","first-page":"cnab014","DOI":"10.1093\/comnet\/cnab014","article-title":"Multi-scale attributed node embedding","volume":"9","author":"Rozemberczki","year":"2021","journal-title":"J. Complex Netw."},{"key":"10.1016\/j.patcog.2026.113877_b26","unstructured":"O. Platonov, D. Kuznedelev, M. Diskin, A. Babenko, L. Prokhorenkova, A critical look at the evaluation of GNNs under heterophily: are we really making progress?, in: The Eleventh International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.patcog.2026.113877_b27","doi-asserted-by":"crossref","unstructured":"Y. Liu, W. Tu, S. Zhou, X. Liu, L. Song, X. Yang, E. Zhu, Deep Graph Clustering via Dual Correlation Reduction, in: Proc. of AAAI, Vol. 36, 2022, pp. 7603\u20137611.","DOI":"10.1609\/aaai.v36i7.20726"},{"key":"10.1016\/j.patcog.2026.113877_b28","article-title":"Rethinking graph auto-encoder models for attributed graph clustering","author":"Mrabah","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.patcog.2026.113877_b29","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b30","series-title":"Are heterophily-specific GNNs and homophily metrics really effective? evaluation pitfalls and new benchmarks","author":"Luan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113877_b31","doi-asserted-by":"crossref","unstructured":"C. Wang, S. Pan, R. Hu, G. Long, J. Jiang, C. Zhang, Attributed Graph Clustering: A Deep Attentional Embedding Approach, in: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 3670\u20133676.","DOI":"10.24963\/ijcai.2019\/509"},{"key":"10.1016\/j.patcog.2026.113877_b32","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.neucom.2021.06.058","article-title":"Multi-scale graph attention subspace clustering network","volume":"459","author":"Wang","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113877_b33","unstructured":"H. Zhu, P. Koniusz, Simple Spectral Graph Convolution, in: 9th International Conference on Learning Representations, ICLR 2021,, 2021."},{"issue":"12","key":"10.1016\/j.patcog.2026.113877_b34","doi-asserted-by":"crossref","first-page":"10851","DOI":"10.1109\/TNNLS.2022.3171583","article-title":"Collaborative decision-reinforced self-supervision for attributed graph clustering","volume":"34","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b35","series-title":"Rwr-gae: Random walk regularization for graph auto encoders","author":"Huang","year":"2019"},{"issue":"6","key":"10.1016\/j.patcog.2026.113877_b36","doi-asserted-by":"crossref","first-page":"2475","DOI":"10.1109\/TCYB.2019.2932096","article-title":"Learning graph embedding with adversarial training methods","volume":"50","author":"Pan","year":"2019","journal-title":"IEEE Trans. Cybern."},{"issue":"6","key":"10.1016\/j.patcog.2026.113877_b37","doi-asserted-by":"crossref","first-page":"7257","DOI":"10.1109\/TCSS.2024.3401218","article-title":"Deep masked graph node clustering","volume":"11","author":"Yang","year":"2024","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b38","doi-asserted-by":"crossref","unstructured":"P. Zhu, Q. Wang, Y. Wang, J. Li, Q. Hu, Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 17184\u201317192.","DOI":"10.1609\/aaai.v38i15.29664"},{"key":"10.1016\/j.patcog.2026.113877_b39","series-title":"International Conference on Machine Learning","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","author":"Hassani","year":"2020"},{"key":"10.1016\/j.patcog.2026.113877_b40","doi-asserted-by":"crossref","unstructured":"D. Bo, X. Wang, C. Shi, M. Zhu, E. Lu, P. Cui, Structural deep clustering network, in: Proceedings of the Web Conference 2020, 2020, pp. 1400\u20131410.","DOI":"10.1145\/3366423.3380214"},{"key":"10.1016\/j.patcog.2026.113877_b41","doi-asserted-by":"crossref","unstructured":"W. Tu, S. Zhou, X. Liu, X. Guo, Z. Cai, E. Zhu, J. Cheng, Deep fusion clustering network, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 9978\u20139987.","DOI":"10.1609\/aaai.v35i11.17198"},{"issue":"10","key":"10.1016\/j.patcog.2026.113877_b42","doi-asserted-by":"crossref","first-page":"13789","DOI":"10.1109\/TNNLS.2023.3271871","article-title":"Simple contrastive graph clustering","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b43","doi-asserted-by":"crossref","unstructured":"X. Yang, Y. Liu, S. Zhou, S. Wang, W. Tu, Q. Zheng, X. Liu, L. Fang, E. Zhu, Cluster-guided contrastive graph clustering network, in: Proc. of AAAI, 2023.","DOI":"10.1609\/aaai.v37i9.26285"},{"key":"10.1016\/j.patcog.2026.113877_b44","doi-asserted-by":"crossref","unstructured":"G. Cui, J. Zhou, C. Yang, Z. Liu, Adaptive graph encoder for attributed graph embedding, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 976\u2013985.","DOI":"10.1145\/3394486.3403140"},{"key":"10.1016\/j.patcog.2026.113877_b45","series-title":"Proceedings of the 2022 SIAM International Conference on Data Mining","first-page":"370","article-title":"Fine-grained attributed graph clustering","author":"Kang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113877_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107206","article-title":"Robust graph structure learning under heterophily","volume":"185","author":"Xie","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.113877_b47","article-title":"Unsupervised network embedding beyond homophily","author":"Zhong","year":"2022","journal-title":"IEEE Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113877_b48","unstructured":"S. Thakoor, C. Tallec, M.G. Azar, R. Munos, P. Veli\u010dkovi\u0107, M. Valko, Bootstrapped representation learning on graphs, in: ICLR 2021 Workshop on Geometrical and Topological Representation Learning, 2021."},{"key":"10.1016\/j.patcog.2026.113877_b49","series-title":"International Conference on Machine Learning","first-page":"24332","article-title":"ProGCL: Rethinking hard negative mining in graph contrastive learning","author":"Xia","year":"2022"},{"key":"10.1016\/j.patcog.2026.113877_b50","doi-asserted-by":"crossref","first-page":"3248","DOI":"10.52202\/068431-0235","article-title":"S3GC: scalable self-supervised graph clustering","volume":"35","author":"Devvrit","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b51","series-title":"International Conference on Machine Learning","first-page":"21794","article-title":"Dink-net: Neural clustering on large graphs","author":"Liu","year":"2023"},{"issue":"10","key":"10.1016\/j.patcog.2026.113877_b52","doi-asserted-by":"crossref","first-page":"13383","DOI":"10.1109\/TNNLS.2023.3267902","article-title":"Exploiting neighbor effect: Conv-agnostic GNN framework for graphs with heterophily","volume":"35","author":"Chen","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113877_b53","doi-asserted-by":"crossref","unstructured":"B. Li, E. Pan, Z. Kang, Pc-conv: Unifying homophily and heterophily with two-fold filtering, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 13437\u201313445.","DOI":"10.1609\/aaai.v38i12.29246"},{"key":"10.1016\/j.patcog.2026.113877_b54","unstructured":"Y. Zhu, Y. Xu, F. Yu, Q. Liu, S. Wu, L. Wang, Deep Graph Contrastive Representation Learning, in: ICML Workshop on Graph Representation Learning and beyond, 2020."},{"key":"10.1016\/j.patcog.2026.113877_b55","unstructured":"C. Wang, Y. Liu, Y. Yang, W. Li, HeterGCL: graph contrastive learning framework on heterophilic graph, in: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024, pp. 2397\u20132405."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008423?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008423?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T17:17:20Z","timestamp":1781111840000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326008423"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":55,"alternative-id":["S0031320326008423"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113877","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Aggregation-aware MLP: An unsupervised approach for graph message-passing","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113877","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":"113877"}}