{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:06:20Z","timestamp":1784279180024,"version":"3.55.0"},"reference-count":53,"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"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","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.2026.113770","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T23:08:12Z","timestamp":1776294492000},"page":"113770","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["VPF: Topology-preserving Virtual Path Fusion to tackle over-squashing"],"prefix":"10.1016","volume":"179","author":[{"given":"Huiwen","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhong","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiarun","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoren","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113770_b1","unstructured":"Thomas N. Kipf, Max Welling, Semi-supervised classification with graph convolutional networks, in: ICLR, 2017."},{"key":"10.1016\/j.patcog.2026.113770_b2","article-title":"Enhancing graph neural networks on SPD manifolds via cholesky decomposition","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113770_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111825","article-title":"Semi-template framework for retrosynthesis prediction using graph neural network","author":"Ye","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113770_b4","article-title":"Enhancing point cloud feature representation via historical node state increments in graph neural networks","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"issue":"8","key":"10.1016\/j.patcog.2026.113770_b5","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1038\/s42256-025-01087-7","article-title":"Kolmogorov\u2013arnold graph neural networks for molecular property prediction","volume":"7","author":"Li","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113770_b6","unstructured":"Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, Michael M Bronstein, Understanding over-squashing and bottlenecks on graphs via curvature, in: ICLR, 2022."},{"key":"10.1016\/j.patcog.2026.113770_b7","first-page":"27890","article-title":"How wide and how deep? Mitigating over-squashing of GNNs via channel capacity constrained estimation","volume":"vol. 40","author":"You","year":"2026"},{"key":"10.1016\/j.patcog.2026.113770_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111020","article-title":"Collaborative graph neural networks for augmented graphs: A local-to-global perspective","volume":"158","author":"Guo","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113770_b9","unstructured":"Diaaeldin Taha, James Chapman, Marzieh Eidi, Karel Devriendt, Guido Montufar, Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing, in: ICLR, 2025."},{"key":"10.1016\/j.patcog.2026.113770_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130389","article-title":"Over-squashing in graph neural networks: A comprehensive survey","author":"Akansha","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113770_b11","unstructured":"Uri Alon, Eran Yahav, On the bottleneck of graph neural networks and its practical implications, in: ICLR, 2021."},{"issue":"2","key":"10.1016\/j.patcog.2026.113770_b12","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1007\/s13042-024-02326-w","article-title":"Design your own universe: A physics-informed agnostic method for enhancing graph neural networks","volume":"16","author":"Shi","year":"2025","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.patcog.2026.113770_b13","series-title":"International Conference on Machine Learning","first-page":"37051","article-title":"Mitigating over-squashing in graph neural networks by spectrum-preserving sparsification","author":"Liang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113770_b14","unstructured":"Tongzhou Liao, Barnab\u2019as P\u2019oczos, Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention, in: ICLR, 2024."},{"key":"10.1016\/j.patcog.2026.113770_b15","article-title":"A generalization of transformer networks to graphs","author":"Dwivedi","year":"2021","journal-title":"AAAI Work. Deep. Learn. Graphs: Methods Appl."},{"key":"10.1016\/j.patcog.2026.113770_b16","article-title":"Tgformer: Towards temporal graph transformer with auto-correlation mechanism","author":"Chen","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113770_b17","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.patrec.2024.11.004","article-title":"Graph neural networks with maximal independent set-based pooling: Mitigating over-smoothing and over-squashing","volume":"187","author":"Stanovic","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.113770_b18","doi-asserted-by":"crossref","unstructured":"Wei Shen, Mang Ye, Wenke Huang, Resisting over-smoothing in graph neural networks via dual-dimensional decoupling, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 5800\u20135809.","DOI":"10.1145\/3664647.3681204"},{"key":"10.1016\/j.patcog.2026.113770_b19","series-title":"NeurIPS 31","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.patcog.2026.113770_b20","unstructured":"Albert Gu, Tri Dao, Mamba: Linear-time sequence modeling with selective state spaces, in: First Conference on Language Modeling, 2024."},{"key":"10.1016\/j.patcog.2026.113770_b21","unstructured":"Kedar Karhadkar, Pradeep Kr. Banerjee, Guido Mont\u00fafar, FoSR: First-order spectral rewiring for addressing oversquashing in GNNs, in: ICLR, 2023."},{"key":"10.1016\/j.patcog.2026.113770_b22","series-title":"LoG","article-title":"Cayley graph propagation","author":"Wilson","year":"2024"},{"key":"10.1016\/j.patcog.2026.113770_b23","unstructured":"Celia Rubio-Madrigal, Adarsh Jamadandi, Rebekka Burkholz, GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring, in: ICLR, 2025."},{"key":"10.1016\/j.patcog.2026.113770_b24","unstructured":"Mitchell Black, Zhengchao Wan, Amir Nayyeri, Yusu Wang, Understanding oversquashing in GNNs through the lens of effective resistance, in: ICML, 2023."},{"key":"10.1016\/j.patcog.2026.113770_b25","doi-asserted-by":"crossref","first-page":"19650","DOI":"10.52202\/075280-0863","article-title":"Graph convolutional kernel machine versus graph convolutional networks","volume":"36","author":"Wu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113770_b26","unstructured":"Khang Nguyen, Nong Minh Hieu, Vinh Duc Nguyen, Nhat Ho, Stanley Osher, Tan Minh Nguyen, Revisiting over-smoothing and over-squashing using ollivier-ricci curvature, in: ICML, 2023."},{"key":"10.1016\/j.patcog.2026.113770_b27","doi-asserted-by":"crossref","first-page":"10348","DOI":"10.52202\/079017-0331","article-title":"Spectral graph pruning against over-squashing and over-smoothing","volume":"37","author":"Jamadandi","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"10.1016\/j.patcog.2026.113770_b28","doi-asserted-by":"crossref","first-page":"6330","DOI":"10.1109\/TKDE.2024.3397692","article-title":"Graph rewiring and preprocessing for graph neural networks based on effective resistance","volume":"36","author":"Shen","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.patcog.2026.113770_b29","doi-asserted-by":"crossref","unstructured":"Hugo Attali, Thomas Papastergiou, Nathalie Pernelle, Fragkiskos D Malliaros, Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks, in: Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025, pp. 87\u201397.","DOI":"10.1145\/3746252.3760998"},{"issue":"5","key":"10.1016\/j.patcog.2026.113770_b30","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.3390\/electronics14051047","article-title":"Efficient graph representation learning by non-local information exchange","volume":"14","author":"Wei","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.patcog.2026.113770_b31","series-title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113770_b32","unstructured":"Jinsong Chen, Kaiyuan Gao, Gaichao Li, Kun He, NAGphormer: A tokenized graph transformer for node classification in large graphs, in: ICLR, 2023."},{"key":"10.1016\/j.patcog.2026.113770_b33","unstructured":"Dongqi Fu, Zhigang Hua, Yan Xie, Jin Fang, Si Zhang, Kaan Sancak, Hao Wu, Andrey Malevich, Jingrui He, Bo Long, VCR-graphormer: A mini-batch graph transformer via virtual connections, in: ICLR, 2024."},{"key":"10.1016\/j.patcog.2026.113770_b34","doi-asserted-by":"crossref","DOI":"10.1109\/TBDATA.2024.3524081","article-title":"Ntformer: A composite node tokenized graph transformer for node classification","author":"Chen","year":"2025","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.patcog.2026.113770_b35","unstructured":"Dexiong Chen, Till Schulz, Karsten Borgwardt, Learning Long Range Dependencies on Graphs via Random Walks, in: ICLR, 2025."},{"key":"10.1016\/j.patcog.2026.113770_b36","series-title":"KDD","article-title":"Graph mamba: Towards learning on graphs with state space models","author":"Behrouz","year":"2024"},{"key":"10.1016\/j.patcog.2026.113770_b37","series-title":"State Space Modeling of Time Series","author":"Aoki","year":"2013"},{"key":"10.1016\/j.patcog.2026.113770_b38","series-title":"ICLR","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113770_b39","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, Xinggang Wang, Vision mamba: Efficient visual representation learning with bidirectional state space model, in: ICML, 2024."},{"key":"10.1016\/j.patcog.2026.113770_b40","unstructured":"Tri Dao, Albert Gu, Transformers are SSMs: generalized models and efficient algorithms through structured state space duality, in: ICML, 2024."},{"key":"10.1016\/j.patcog.2026.113770_b41","unstructured":"Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, Stefanie Jegelka, Representation learning on graphs with jumping knowledge networks, in: ICML, 2018."},{"key":"10.1016\/j.patcog.2026.113770_b42","volume":"vol. 92","author":"Chung","year":"1997"},{"key":"10.1016\/j.patcog.2026.113770_b43","doi-asserted-by":"crossref","unstructured":"Daniel A. Spielman, Nikhil Srivastava, Graph sparsification by effective resistances, in: Proceedings of the Fortieth Annual ACM Symposium on Theory of Computing, 2008, pp. 563\u2013568.","DOI":"10.1145\/1374376.1374456"},{"issue":"10","key":"10.1016\/j.patcog.2026.113770_b44","doi-asserted-by":"crossref","first-page":"2491","DOI":"10.1016\/j.laa.2011.02.024","article-title":"Effective graph resistance","volume":"435","author":"Ellens","year":"2011","journal-title":"Linear Algebra Appl."},{"key":"10.1016\/j.patcog.2026.113770_b45","article-title":"Dspar: An embarrassingly simple strategy for efficient GNN training and inference via degree-based sparsification","author":"Liu","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"issue":"1","key":"10.1016\/j.patcog.2026.113770_b46","first-page":"1","article-title":"Multi-scale attributed node embedding","volume":"9","author":"Rozemberczki","year":"2021","journal-title":"J. Complex Networks"},{"issue":"2","key":"10.1016\/j.patcog.2026.113770_b47","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":"Inf. Retr."},{"issue":"3","key":"10.1016\/j.patcog.2026.113770_b48","first-page":"93","article-title":"Collective classification in network data","volume":"29","author":"Sen","year":"2008","journal-title":"AI Mag."},{"key":"10.1016\/j.patcog.2026.113770_b49","unstructured":"Christopher Morris, Nils M. Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, Marion Neumann, TUDataset: A collection of benchmark datasets for learning with graphs, in: ICML, 2020."},{"key":"10.1016\/j.patcog.2026.113770_b50","series-title":"NeurIPS","article-title":"Diffusion improves graph learning","author":"Gasteiger","year":"2019"},{"key":"10.1016\/j.patcog.2026.113770_b51","unstructured":"Jeongwhan Choi, Sumin Park, Hyowon Wi, Sung-Bae Cho, Noseong Park, PANDA: Expanded Width-Aware Message Passing Beyond Rewiring, in: ICML, 2024."},{"key":"10.1016\/j.patcog.2026.113770_b52","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, Stefanie Jegelka, How Powerful are Graph Neural Networks?, in: ICLR, 2019."},{"key":"10.1016\/j.patcog.2026.113770_b53","series-title":"International Conference on Neural Information Processing","first-page":"466","article-title":"Mitigating oversmoothing in GNNs across diverse graph domains","author":"Varshney","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007351?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007351?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:29:47Z","timestamp":1784276987000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":53,"alternative-id":["S0031320326007351"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113770","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":"VPF: Topology-preserving Virtual Path Fusion to tackle over-squashing","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113770","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":"113770"}}