{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T01:43:38Z","timestamp":1772070218091,"version":"3.50.1"},"reference-count":185,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Research Council Project PSAP","award":["101002047"],"award-info":[{"award-number":["101002047"]}]},{"name":"European High-Performance Computing Joint Undertaking","award":["955513"],"award-info":[{"award-number":["955513"]}]},{"name":"ETH Future Computing Laboratory"},{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union’s HE Research and Innovation Programme","award":["101070141"],"award-info":[{"award-number":["101070141"]}]},{"name":"Polish high-performance computing infrastructure PLGrid","award":["PLG\/2024\/017103"],"award-info":[{"award-number":["PLG\/2024\/017103"]}]},{"name":"Swiss AI Initiative for the computational grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3637114","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T18:28:44Z","timestamp":1764095324000},"page":"2544-2565","source":"Crossref","is-referenced-by-count":1,"title":["Demystifying Higher-Order Graph Neural Networks"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6550-7916","authenticated-orcid":false,"given":"Maciej","family":"Besta","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"given":"Florian","family":"Scheidl","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"given":"Lukas","family":"Gianinazzi","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"given":"Grzegorz","family":"Kwasniewski","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"given":"Shachar","family":"Klaiman","sequence":"additional","affiliation":[{"name":"BASF SE, Ludwigshafen, Germany"}]},{"given":"J\u00fcrgen","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"BASF SE, Ludwigshafen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]}],"member":"263","reference":[{"key":"ref1","first-page":"21","article-title":"MixHop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abu-El-Haija","year":"2019"},{"key":"ref2","volume-title":"SLIC Superpixels","author":"Achanta","year":"2010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"ref4","first-page":"8017","article-title":"Subgraph Neural Networks","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Alsentzer","year":"2020"},{"issue":"5","key":"ref5","first-page":"586","article-title":"Evolutionary dynamics of higher-order interactions in social networks","volume-title":"Nature Hum. Behav.","volume":"5","author":"Alvarez-Rodriguez","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3605776"},{"key":"ref7","article-title":"A hypergraph neural network framework for learning hyperedge-dependent node embeddings","author":"Aponte","year":"2022"},{"key":"ref8","article-title":"On vanishing gradients, over-smoothing, and over-squashing in GNNs: Bridging recurrent and graph learning","volume-title":"Proc. 39th Conf. Neural Inf. Process. Syst.","author":"Arroyo","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22177-9_26"},{"key":"ref10","article-title":"Hypersage: Generalizing inductive representation learning on hypergraphs","author":"Arya","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3434483"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2897518.2897542"},{"key":"ref13","article-title":"Hypergraph convolution and hypergraph attention","volume-title":"Pattern Recognit.","volume":"110","author":"Bai","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3065737"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-5026-8_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545082"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3209"},{"key":"ref18","first-page":"11423","article-title":"Mace: Higher order equivariant message passing neural networks for fast and accurate force fields","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Batatia","year":"2022"},{"issue":"10","key":"ref19","first-page":"1093","article-title":"The physics of higher-order interactions in complex systems","volume-title":"Nature Phys.","volume":"17","author":"Battiston","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2020.05.004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/science.aad9029"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref23","article-title":"Hot: Higher-order dynamic graph representation learning with efficient transformers","volume-title":"Proc. Learn. Graphs Conf.","author":"Besta","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539343"},{"key":"ref25","article-title":"Survey and taxonomy of lossless graph compression and space-efficient graph representations","author":"Besta","year":"2018"},{"key":"ref26","first-page":"31","article-title":"Neural graph databases","volume-title":"Proc. Learn. Graphs Conf.","author":"Besta","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607067"},{"key":"ref28","first-page":"1","article-title":"Equivariant subgraph aggregation networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bevilacqua","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/21m1414024"},{"key":"ref30","first-page":"2625","article-title":"Weisfeiler and Lehman go cellular: CW networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Bodnar","year":"2021"},{"key":"ref31","first-page":"1026","article-title":"Weisfeiler and Lehman go topological: Message passing simplicial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bodnar","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1067"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3154319"},{"key":"ref34","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","author":"Bronstein","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref36","article-title":"Graph convolutions that can finally model local structure","author":"Brossard","year":"2020"},{"key":"ref37","volume-title":"Linear Algebraic Primitives for Parallel Computing on Large Graphs","author":"Buluc","year":"2010"},{"key":"ref38","first-page":"1","article-title":"Simplicial 2-Complex convolutional neural nets","volume-title":"Proc. Topolog. Data Anal. Beyond Workshop 34th Conf. Neural Inf. Process. Syst.","author":"Bunch","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/bf01305232"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"issue":"89","key":"ref41","first-page":"1","article-title":"Machine learning on graphs: A model and comprehensive taxonomy","volume":"23","author":"Chami","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058098"},{"key":"ref43","first-page":"1","article-title":"fuseGNN: Accelerating graph convolutional neural network training on GPGPU","volume-title":"Proc. IEEE\/ACM Int. Conf. Comput. Aided Des.","author":"Chen","year":"2020"},{"key":"ref44","first-page":"10383","article-title":"Can graph neural networks count substructures?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen","year":"2020"},{"key":"ref45","first-page":"15894","article-title":"On the equivalence between graph isomorphism testing and function approximation with GNNs","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3655103.3655110"},{"key":"ref47","first-page":"1","article-title":"You are AllSet: A multiset function framework for hypergraph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/net.3230110103"},{"key":"ref49","article-title":"Reconstruction for powerful graph representations","author":"Cotta","year":"2021"},{"key":"ref50","first-page":"1","article-title":"HNHN: Hypergraph networks with hyperedge neurons","volume-title":"Proc. Graph Representation Learn.","author":"Dong","year":"2020"},{"key":"ref51","first-page":"1","article-title":"Simplicial neural networks","volume-title":"Proc. Topological Data Anal. Beyond Workshop 34th Conf. Neural Inf. Process. Syst.","author":"Ebli","year":"2020"},{"key":"ref52","article-title":"Continuous simplicial neural networks","author":"Einizade","year":"2025"},{"key":"ref53","first-page":"4776","article-title":"How powerful are k-hop message passing graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Feng","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"ref55","article-title":"Fast graph representation learning with pytorch geometric","author":"Fey","year":"2019"},{"key":"ref56","first-page":"1","article-title":"Hierarchical inter-message passing for learning on molecular graphs","volume-title":"Graph Representation Learn.","author":"Fey","year":"2020"},{"key":"ref57","first-page":"31376","article-title":"Understanding and extending subgraph GNNs by rethinking their symmetries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Frasca","year":"2022"},{"key":"ref58","first-page":"1","article-title":"SIGN: Scalable inception graph neural networks","volume-title":"Graph Representation Learn.","author":"Frasca","year":"2020"},{"key":"ref59","first-page":"6878","article-title":"$ p$p-Laplacian based graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.068"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33833"},{"key":"ref62","article-title":"The expressive power of kth-order invariant graph networks","author":"Geerts","year":"2020"},{"key":"ref63","first-page":"1","article-title":"Expressiveness and approximation properties of graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geerts","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503286"},{"key":"ref65","article-title":"Learning combinatorial node labeling algorithms","author":"Gianinazzi","year":"2021"},{"key":"ref66","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614997"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10827-016-0608-6"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191530"},{"key":"ref70","first-page":"1","article-title":"Simplicial attention networks","volume-title":"Proc. Workshop Geometrical Topological Representation Learn.","author":"Goh","year":"2022"},{"issue":"7666","key":"ref71","first-page":"210","article-title":"Higher-order interactions stabilize dynamics in competitive network models","volume-title":"Nature","volume":"548","author":"Grilli","year":"2017"},{"key":"ref72","article-title":"Awesome TNNs","author":"Hajij","year":"2023"},{"key":"ref73","article-title":"Cell complex neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Workshop TDA Beyond","author":"Hajij","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF59524.2023.10477018"},{"key":"ref75","article-title":"Simplicial complex representation learning","volume-title":"Proc. Mach. Learn. Graphs Workshop 15th ACM Int. WSDM Conf.","author":"Hajij","year":"2022"},{"key":"ref76","article-title":"Topological deep learning: Going beyond graph data","author":"Hajij","year":"2023"},{"key":"ref77","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hamilton","year":"2017"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.2200\/S01045ED1V01Y202009AIM046"},{"key":"ref79","article-title":"Representation learning on graphs: Methods and applications","author":"Hamilton","year":"2018"},{"key":"ref80","article-title":"Graph isomorphisms in quasi-polynomial time","author":"Helfgott","year":"2017"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15931-2_48"},{"key":"ref82","article-title":"Efficient distribution for deep learning on large graphs","author":"Hoang","year":"2021"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/800119.803896"},{"key":"ref84","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hu","year":"2020"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/353"},{"key":"ref86","article-title":"Boosting the cycle counting power of graph neural networks with I2-GNNs","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Huang","year":"2022"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746349"},{"key":"ref88","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with ROC","volume-title":"Proc. Mach. Learn. Syst.","author":"Jia","year":"2020"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/371"},{"issue":"1","key":"ref90","first-page":"961","article-title":"A congruence theorem for trees","volume-title":"Pacific J. Math.","volume":"7","author":"Kelly","year":"1957"},{"key":"ref91","article-title":"Power and limits of the Weisfeiler-Leman algorithm","author":"Kiefer"},{"key":"ref92","article-title":"Efficient representation learning of subgraphs by subgraph-to-node translation","author":"Kim","year":"2022"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01459"},{"key":"ref94","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357880"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313461"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539258"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512206"},{"key":"ref101","article-title":"Higher-order weighted graph convolutional networks","author":"Liu","year":"2019"},{"key":"ref102","first-page":"18779","article-title":"SHINE: SubHypergraph inductive neural network","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Luo","year":"2022"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539299"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2017.95"},{"key":"ref105","article-title":"Provably powerful graph networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Maron","year":"2019"},{"key":"ref106","first-page":"1","article-title":"Invariant and equivariant graph networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maron","year":"2019"},{"key":"ref107","article-title":"On the universality of invariant networks","author":"Maron","year":"2019"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"ref109","article-title":"Introduction to Topology","author":"Mendelson","year":"2012"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11747"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/DSW.2018.8439897"},{"key":"ref112","first-page":"1","article-title":"TUDataset: A collection of benchmark datasets for learning with graphs","volume-title":"Graph Representation Learn.","author":"Morris","year":"2020"},{"issue":"333","key":"ref113","first-page":"1","article-title":"Weisfeiler and Leman go machine learning: The story so far","volume":"24","author":"Morris","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref114","first-page":"21824","article-title":"Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Morris","year":"2020"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1112\/s0024611503014412"},{"key":"ref117","first-page":"25956","article-title":"Revisiting over-smoothing and over-squashing using ollivier-ricci curvature","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen","year":"2023"},{"key":"ref118","article-title":"Position: Topological deep learning is the new frontier for relational learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Papamarkou","year":"2024"},{"key":"ref119","article-title":"Architectures of topological deep learning: A survey on topological neural networks","author":"Papillon","year":"2023"},{"key":"ref120","first-page":"21997","article-title":"DropGNN: Random dropouts increase the expressiveness of graph neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Papp","year":"2021"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33460-3_32"},{"key":"ref122","first-page":"28191","article-title":"Equivariant polynomials for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Puny","year":"2023"},{"key":"ref123","first-page":"21030","article-title":"Ordered subgraph aggregation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Qian","year":"2022"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049000"},{"key":"ref125","first-page":"1","article-title":"DropEdge: Towards deep graph convolutional networks on node classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rong","year":"2020"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186900"},{"key":"ref127","article-title":"HONE: Higher-order network embeddings","author":"Rossi","year":"2018"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414015"},{"key":"ref129","article-title":"A survey on the expressive power of graph neural networks","author":"Sato","year":"2020"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1137\/18M1201019"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.108149"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.33564\/ijeast.2020.v04i12.054"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3380643"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00036"},{"key":"ref135","article-title":"Demystifying topological message-passing with relational structures: A case study on oversquashing in simplicial message-passing","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Taha"},{"key":"ref136","first-page":"16","article-title":"Measuring higher-order drug interactions: A review of recent approaches","volume-title":"Curr. Opin. Syst. Biol.","volume":"4","author":"Tekin","year":"2017"},{"key":"ref137","article-title":"Topobenchmarkx: A framework for benchmarking topological deep learning","author":"Telyatnikov","year":"2024"},{"key":"ref138","first-page":"29922","article-title":"Autobahn: Automorphism-based graph neural nets","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Thiede","year":"2021"},{"key":"ref139","article-title":"Dorylus: Affordable, scalable, and accurate GNN training over billion-edge graphs","author":"Thorpe","year":"2021"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1137\/20M1355896"},{"key":"ref141","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"ref142","article-title":"Marius: Large-scale training of graph neural networks on a single machine","author":"Waleffe","year":"2022"},{"key":"ref143","article-title":"PipeGCN: Efficient full-graph training of graph convolutional networks with pipelined feature communication","author":"Wan","year":"2022"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/183"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"ref146","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2019"},{"key":"ref147","first-page":"1","article-title":"Equivariant hypergraph diffusion neural operators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2963367"},{"key":"ref149","article-title":"Pytorch geometric high order: A unified library for high order graph neural network","author":"Wang","year":"2023"},{"key":"ref150","article-title":"An empirical study of realized GNN expressiveness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2024"},{"key":"ref151","article-title":"GNNadvisor: An efficient runtime system for GNN acceleration on GPUs","volume-title":"Proc. Symp. Operating Syst. Des. Implementation","author":"Wang","year":"2021"},{"key":"ref152","first-page":"17:1","article-title":"Towards efficient and expressive GNNs for graph classification via subgraph-aware Weisfeiler-Lehman","volume-title":"Proc. 1st Learn. Graphs Conf.","author":"Wang","year":"2022"},{"key":"ref153","article-title":"The reduction of a graph to canonical form and the algebra which appears therein","volume":"9","author":"Weisfeiler","year":"1968","journal-title":"Nauchno-Technicheskaya Informatsia"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456247"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref156","first-page":"1","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2019"},{"key":"ref157","first-page":"3275","article-title":"Neural message passing for multi-relational ordered and recursive hypergraphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yadati","year":"2020"},{"key":"ref158","first-page":"30:1","article-title":"Oversquashing in hypergraph neural networks","volume-title":"Proc. 3rd Learn. Graphs Conf.","author":"Yadati","year":"2024"},{"key":"ref159","article-title":"HyperGCN: A new method for training graph convolutional networks on hypergraphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yadati","year":"2019"},{"key":"ref160","article-title":"Convolutional learning on simplicial complexes","author":"Yang","year":"2023"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746017"},{"key":"ref162","first-page":"13","article-title":"Efficient representation learning for higher-order data with simplicial complexes","volume-title":"Proc. Learn. Graphs Conf.","author":"Yang","year":"2022"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11836"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref166","first-page":"3391","article-title":"Deep Sets","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zaheer","year":"2017"},{"key":"ref167","first-page":"41019","article-title":"A complete expressiveness hierarchy for subgraph GNNs via subgraph weisfeiler-lehman tests","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2023"},{"key":"ref168","first-page":"1","article-title":"Beyond Weisfeiler-Lehman: A quantitative framework for GNN expressiveness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415539"},{"key":"ref170","article-title":"Hypergraph convolutional networks via equivalency between hypergraphs and undirected graphs","author":"Zhang","year":"2022"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00036"},{"key":"ref172","first-page":"15734","article-title":"Nested graph neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref173","first-page":"1","article-title":"Hyper-SAGNN: A self-sttention based graph neural network for hypergraphs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref174","article-title":"GMLP: Building scalable and flexible graph neural networks with feature-message passing","author":"Zhang","year":"2021"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511986"},{"issue":"01","key":"ref176","first-page":"249","article-title":"Deep learning on graphs: A survey","volume-title":"IEEE Trans. Knowl. Data Eng.","volume":"34","author":"Zhang","year":"2022"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.3390\/app10228160"},{"key":"ref178","first-page":"1","article-title":"From stars to subgraphs: Uplifting any GNN with local structure awareness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2022"},{"key":"ref179","first-page":"34106","article-title":"A practical, progressively-expressive GNN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhao","year":"2022"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539177"},{"key":"ref181","first-page":"42742","article-title":"From relational pooling to subgraph GNNs: A universal framework for more expressive graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2023"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0205"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref184","first-page":"14293","article-title":"Distance-restricted folklore weisfeiler-leman GNNs with provable cycle counting power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhou","year":"2023"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11267259.pdf?arnumber=11267259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:06:13Z","timestamp":1770671173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11267259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":185,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3637114","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}