{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:04:31Z","timestamp":1770743071381,"version":"3.49.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>\n                    <jats:bold>Graph Neural Networks (GNNs)<\/jats:bold>\n                    with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often overlook the over-smoothing issue caused by traditional GNN models, as well as the gradient explosion or vanishing problems in deep GNNs. (2) Most models operate on first-order information, neglecting that the real world often consists of second-order systems, which further limits the model\u2019s representation capabilities. To address these issues, we propose the\n                    <jats:bold>Dual Second-order Equivariant Graph Ordinary (DuSEGO)<\/jats:bold>\n                    Differential Equation for equivariant representation. Specifically, DuSEGO applies the dual second-order equivariant graph ordinary differential equations (Graph ODEs) to both graph embeddings and node coordinates simultaneously. Theoretically, we first prove that DuSEGO maintains the equivariant property. Furthermore, we provide theoretical insights showing that DuSEGO effectively alleviates the over-smoothing problem in both feature representation and coordinate update. Additionally, we demonstrate that the proposed DuSEGO mitigates the exploding and vanishing gradients problem, facilitating the training of deep multi-layer GNNs. Extensive experiments on benchmark datasets validate the superiority of the proposed DuSEGO compared to baselines.\n                  <\/jats:p>","DOI":"10.1145\/3774321","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T10:57:23Z","timestamp":1762167443000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DuSEGO: Dual Second-Order Equivariant Graph Ordinary Differential Equation"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-1464","authenticated-orcid":false,"given":"Yingxu","family":"Wang","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4979-3955","authenticated-orcid":false,"given":"Nan","family":"Yin","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6184-355X","authenticated-orcid":false,"given":"Mingyan","family":"Xiao","sequence":"additional","affiliation":[{"name":"California State Polytechnic University, Pomona, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1882-0236","authenticated-orcid":false,"given":"Xinhao","family":"Yi","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7326-2883","authenticated-orcid":false,"given":"Siwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1625-2168","authenticated-orcid":false,"given":"Shangsong","family":"Liang","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates and Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Anderson Brandon","year":"2019","unstructured":"Brandon Anderson, Truong Son Hy, and Risi Kondor. 2019. Cormorant: Covariant molecular neural networks. In Advances in Neural Information Processing Systems, Vol. 32, 1\u201310."},{"key":"e_1_3_2_3_2","first-page":"1","article-title":"Interaction networks for learning about objects, relations and physics","volume":"29","author":"Battaglia Peter","year":"2016","unstructured":"Peter Battaglia, Razvan Pascanu, Matthew Lai, and Danilo Jimenez Rezende. 2016. Interaction networks for learning about objects, relations and physics. In Advances in Neural Information Processing Systems, Vol. 29, 1\u20139.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_4_2","unstructured":"Kamal Berahmand Farid Saberi-Movahed Razieh Sheikhpour Yuefeng Li and Mahdi Jalili. 2025. A comprehensive survey on spectral clustering with graph structure learning. arXiv:2501.13597. Retrieved from https:\/\/arxiv.org\/abs\/2501.13597"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acb03e"},{"key":"e_1_3_2_6_2","unstructured":"Suresh Bishnoi Ravinder Bhattoo Sayan Ranu and N. M. Krishnan. 2022. Enhancing the inductive biases of graph neural ode for modeling dynamical systems. arXiv:2209.10740. Retrieved from https:\/\/arxiv.org\/abs\/2209.10740"},{"key":"e_1_3_2_7_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Brandstetter Johannes","year":"2021","unstructured":"Johannes Brandstetter, Rob Hesselink, Elise van der Pol, Erik J. Bekkers, and Max Welling. 2021. Geometric and physical quantities improve E(3) equivariant message passing. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_8_2","first-page":"1","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen Ricky T. Q.","year":"2018","unstructured":"Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, and David K. Duvenaud. 2018. Neural ordinary differential equations. In Advances in Neural Information Processing Systems, Vol. 31, 1\u201313.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_9_2","first-page":"2456","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Dasoulas George","year":"2021","unstructured":"George Dasoulas, Kevin Scaman, and Aladin Virmaux. 2021. Lipschitz normalization for self-attention layers with application to graph neural networks. In Proceedings of the International Conference on Machine Learning, 2456\u20132466."},{"key":"e_1_3_2_10_2","first-page":"66647","article-title":"A new perspective on building efficient and expressive 3D equivariant graph neural networks","volume":"36","author":"Du Yuanqi","year":"2024","unstructured":"Yuanqi Du, Limei Wang, Dieqiao Feng, Guifeng Wang, Shuiwang Ji, Carla P. Gomes, and Zhi-Ming Ma. 2024. A new perspective on building efficient and expressive 3D equivariant graph neural networks. In Advances in Neural Information Processing Systems, Vol. 36, 66647\u201366674.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.5486\/PMD.1959.6.3-4.12"},{"key":"e_1_3_2_12_2","first-page":"1970","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Fuchs Fabian","year":"2020","unstructured":"Fabian Fuchs, Daniel Worrall, Volker Fischer, and Max Welling. 2020. SE(3)-transformers: 3D roto-translation equivariant attention networks. In Advances in Neural Information Processing Systems, Vol. 33, 1970\u20131981."},{"key":"e_1_3_2_13_2","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems Workshop","author":"Gasteiger Johannes","year":"2020","unstructured":"Johannes Gasteiger, Shankari Giri, Johannes T. Margraf, and Stephan G\u00fcnnemann. 2020. Fast and uncertainty-aware directional message passing for non-equilibrium molecules. In Proceedings of the International Conference on Neural Information Processing Systems Workshop."},{"key":"e_1_3_2_14_2","first-page":"3996","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Guo Kai","year":"2022","unstructured":"Kai Guo, Kaixiong Zhou, Xia Hu, Yu Li, Yi Chang, and Xin Wang. 2022. Orthogonal graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, 3996\u20134004."},{"key":"e_1_3_2_15_2","first-page":"9176","volume-title":"Proceedings of the Conference on Neural Information Processing Systems","author":"Han Jiaqi","year":"2022","unstructured":"Jiaqi Han, Wenbing Huang, Tingyang Xu, and Yu Rong. 2022. Equivariant graph hierarchy-based neural networks. In Proceedings of the Conference on Neural Information Processing Systems, 9176\u20139187."},{"key":"e_1_3_2_16_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Huang Wenbing","year":"2021","unstructured":"Wenbing Huang, Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun, and Junzhou Huang. 2021. Equivariant graph mechanics networks with constraints. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_17_2","first-page":"16177","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Huang Zijie","year":"2020","unstructured":"Zijie Huang, Yizhou Sun, and Wei Wang. 2020. Learning continuous system dynamics from irregularly-sampled partial observations. In Advances in Neural Information Processing Systems, Vol. 33, 16177\u201316187."},{"key":"e_1_3_2_18_2","first-page":"705","volume-title":"Proceedings of the International ACM SIGKDD Conference on Knowledge Discovery & Data Mining","author":"Huang Zijie","year":"2021","unstructured":"Zijie Huang, Yizhou Sun, and Wei Wang. 2021. Coupled graph ODE for learning interacting system dynamics. In Proceedings of the International ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 705\u2013715."},{"key":"e_1_3_2_19_2","volume-title":"Random Graphs","author":"Janson Svante","year":"2011","unstructured":"Svante Janson, Tomasz Luczak, and Andrzej Rucinski. 2011. Random Graphs. John Wiley & Sons."},{"key":"e_1_3_2_20_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv:2001.08361. Retrieved from https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/nsb0902-646"},{"key":"e_1_3_2_22_2","first-page":"2268","volume-title":"Proceedings of the Conference on Neural Information Processing Systems","author":"Keriven Nicolas","year":"2022","unstructured":"Nicolas Keriven. 2022. Not too little, not too much: A theoretical analysis of graph (over) smoothing. In Proceedings of the Conference on Neural Information Processing Systems, 2268\u20132281."},{"key":"e_1_3_2_23_2","first-page":"2688","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Kipf Thomas","year":"2018","unstructured":"Thomas Kipf, Ethan Fetaya, Kuan-Chieh Wang, Max Welling, and Richard Zemel. 2018. Neural relational inference for interacting systems. In Proceedings of the International Conference on Machine Learning, 2688\u20132697."},{"key":"e_1_3_2_24_2","unstructured":"Thomas N. Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv:1611.07308. Retrieved from https:\/\/arxiv.org\/abs\/1611.07308"},{"key":"e_1_3_2_25_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_26_2","unstructured":"Jonas K\u00f6hler Leon Klein and Frank No\u00e9. 2019. Equivariant flows: Sampling configurations for multi-body systems with symmetric energies. arXiv:1910.00753. Retrieved from https:\/\/arxiv.org\/abs\/1910.00753"},{"key":"e_1_3_2_27_2","first-page":"1","volume-title":"Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201925)","author":"Li Guoming","year":"2025","unstructured":"Guoming Li, Jian Yang, and Shangsong Liang. 2025. ERGNN: Spectral graph neural network with explicitly-optimized rational graph filters. In Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201925). IEEE, 1\u20135."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"e_1_3_2_29_2","unstructured":"Yujia Li Daniel Tarlow Marc Brockschmidt and Richard Zemel. 2015. Gated graph sequence neural networks. arXiv:1511.05493. Retrieved from https:\/\/arxiv.org\/abs\/1511.05493"},{"key":"e_1_3_2_30_2","unstructured":"Ce Liu Jun Wang Zhiqiang Cai Yingxu Wang Huizhen Kuang Kaihui Cheng Liwei Zhang Qingkun Su Yining Tang Fenglei Cao et al. 2024. Dynamic PDB: A new dataset and a SE(3) model extension by integrating dynamic behaviors and physical properties in protein structures. arXiv:2408.12413. Retrieved from https:\/\/arxiv.org\/abs\/2408.12413"},{"key":"e_1_3_2_31_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Liu Yang","year":"2024","unstructured":"Yang Liu, Jiashun Cheng, Haihong Zhao, Tingyang Xu, Peilin Zhao, Fugee Tsung, Jia Li, and Yu Rong. 2024. SEGNO: Generalizing equivariant graph neural networks with physical inductive biases. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_32_2","unstructured":"Yi Liu Limei Wang Meng Liu Xuan Zhang Bora Oztekin and Shuiwang Ji. 2021. Spherical message passing for 3D graph networks. arXiv:2102.05013. Retrieved from https:\/\/arxiv.org\/abs\/2102.05013"},{"key":"e_1_3_2_33_2","first-page":"23124","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Luo Xiao","year":"2023","unstructured":"Xiao Luo, Jingyang Yuan, Zijie Huang, Huiyu Jiang, Yifang Qin, Wei Ju, Ming Zhang, and Yizhou Sun. 2023. Hope: High-order graph ODE for modeling interacting dynamics. In Proceedings of the International Conference on Machine Learning, 23124\u201323139."},{"key":"e_1_3_2_34_2","first-page":"14498","volume-title":"Proceedings of the Conference on Neural Information Processing Systems","author":"Min Yimeng","year":"2020","unstructured":"Yimeng Min, Frederik Wenkel, and Guy Wolf. 2020. Scattering GCN: Overcoming oversmoothness in graph convolutional networks. In Proceedings of the Conference on Neural Information Processing Systems, 14498\u201314508."},{"key":"e_1_3_2_35_2","first-page":"5911","volume-title":"Proceedings of the Conference on Neural Information Processing Systems","author":"Norcliffe Alexander","year":"2020","unstructured":"Alexander Norcliffe, Cristian Bodnar, Ben Day, Nikola Simidjievski, and Pietro Li\u00f2. 2020. On second order behaviour in augmented neural odes. In Proceedings of the Conference on Neural Information Processing Systems, 5911\u20135921."},{"key":"e_1_3_2_36_2","unstructured":"Michael Poli Stefano Massaroli Junyoung Park Atsushi Yamashita Hajime Asama and Jinkyoo Park. 2019. Graph neural ordinary differential equations. arXiv:1911.07532. Retrieved from https:\/\/arxiv.org\/abs\/1911.07532"},{"key":"e_1_3_2_37_2","first-page":"18888","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Rusch T. Konstantin","year":"2022","unstructured":"T. Konstantin Rusch, Ben Chamberlain, James Rowbottom, Siddhartha Mishra, and Michael Bronstein. 2022. Graph-coupled oscillator networks. In Proceedings of the International Conference on Machine Learning, 18888\u201318909."},{"key":"e_1_3_2_38_2","unstructured":"Alvaro Sanchez-Gonzalez Victor Bapst Kyle Cranmer and Peter Battaglia. 2019. Hamiltonian graph networks with ODE integrators. arXiv:1909.12790. Retrieved from https:\/\/arxiv.org\/abs\/1909.12790"},{"key":"e_1_3_2_39_2","first-page":"9323","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Garcia Satorras V\u0131ctor","year":"2021","unstructured":"V\u0131ctor Garcia Satorras, Emiel Hoogeboom, and Max Welling. 2021. E(n) equivariant graph neural networks. In Proceedings of the International Conference on Machine Learning, 9323\u20139332."},{"key":"e_1_3_2_40_2","first-page":"9377","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Sch\u00fctt Kristof","year":"2021","unstructured":"Kristof Sch\u00fctt, Oliver Unke, and Michael Gastegger. 2021. Equivariant message passing for the prediction of tensorial properties and molecular spectra. In Proceedings of the International Conference on Machine Learning, 9377\u20139388."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110882"},{"key":"e_1_3_2_42_2","unstructured":"Nathaniel Thomas Tess Smidt Steven Kearnes Lusann Yang Li Li Kai Kohlhoff and Patrick Riley. 2018. Tensor field networks: Rotation-and translation-equivariant neural networks for 3D point clouds. arXiv:1802.08219. Retrieved from https:\/\/arxiv.org\/abs\/1802.08219"},{"key":"e_1_3_2_43_2","unstructured":"Yingxu Wang Mengzhu Wang Zhichao Huang Suyu Liu and Nan Yin. 2025. Nested graph pseudo-label refinement for noisy label domain adaptation learning. arXiv:2508.00716. Retrieved from https:\/\/arxiv.org\/abs\/2508.00716"},{"key":"e_1_3_2_44_2","volume-title":"Solving Ordinary Differential Equations II","author":"Wanner Gerhard","year":"1996","unstructured":"Gerhard Wanner and Ernst Hairer. 1996. Solving Ordinary Differential Equations II, Vol. 375. Springer Berlin."},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","first-page":"15513","DOI":"10.18653\/v1\/2025.acl-long.755","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Xian Ziting","year":"2025","unstructured":"Ziting Xian, Jiawei Gu, Lingbo Li, and Shangsong Liang. 2025. MolRAG: Unlocking the power of large language models for molecular property prediction. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 15513\u201315531."},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_47_2","first-page":"5708","volume-title":"Proceedings of the International Conference on Machine Learning","author":"You Jiaxuan","year":"2018","unstructured":"Jiaxuan You, Rex Ying, Xiang Ren, William Hamilton, and Jure Leskovec. 2018. GraphRNN: Generating realistic graphs with deep auto-regressive models. In Proceedings of the International Conference on Machine Learning, 5708\u20135717."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-46382-8"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T09:20:17Z","timestamp":1765185617000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3774321"],"URL":"https:\/\/doi.org\/10.1145\/3774321","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,8]]},"assertion":[{"value":"2024-11-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}