{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:44Z","timestamp":1783455464006,"version":"3.55.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["PHY-2117997"],"award-info":[{"award-number":["PHY-2117997"]}]},{"name":"NSF","award":["IIS-2239565"],"award-info":[{"award-number":["IIS-2239565"]}]},{"name":"NSF","award":["IIS-2428777"],"award-info":[{"award-number":["IIS-2428777"]}]},{"name":"NSF","award":["IIS-2435957"],"award-info":[{"award-number":["IIS-2435957"]}]},{"name":"JPMC faculty award 2023"},{"name":"NVIDIA Academic Grant Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3680437","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:53:17Z","timestamp":1775245997000},"page":"10184-10191","source":"Crossref","is-referenced-by-count":0,"title":["How Can State Space Models Enhance Machine Learning on Graphs?"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7076-1628","authenticated-orcid":false,"given":"Yinan","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siqi","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3742-0845","authenticated-orcid":false,"given":"Pan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Duvenaud","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669302"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2021.02.011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2986316"},{"key":"ref7","first-page":"2713","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2016"},{"key":"ref8","first-page":"2920","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"ref9","first-page":"9104","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"ref11","first-page":"8247","article-title":"Understanding over-squashing and bottlenecks on graphs via curvature","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Topping","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1622"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1054"},{"key":"ref17","first-page":"4465","article-title":"Distance encoding: Design provably more powerful neural networks for graph representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li","year":"2020"},{"key":"ref18","first-page":"17029","article-title":"Equivariant and stable positional encoding for more powerful graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref19","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ying","year":"2021"},{"key":"ref20","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Katharopoulos","year":"2020"},{"key":"ref21","first-page":"1060","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choromanski","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.13350"},{"key":"ref24","first-page":"1763","article-title":"Simple linear attention language models balance the recall-throughputtradeoff","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Arora","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1986"},{"key":"ref26","first-page":"31613","article-title":"Exphormer: Sparse transformers for graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shirzad","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/263"},{"key":"ref28","first-page":"17375","article-title":"GOAT: A global transformer on large-scale graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kong","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2826"},{"key":"ref30","first-page":"35546","article-title":"Locality-sensitive hashing-based efficient point transformer with applications in high-energy physics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miao","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref32","first-page":"14323","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2021"},{"key":"ref33","first-page":"173","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu","year":"2025"},{"key":"ref34","first-page":"1474","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Gu","year":"2020"},{"key":"ref35","first-page":"11694","article-title":"Long range arena: A benchmark for efficient transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tay","year":"2021"},{"key":"ref36","article-title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces","author":"Wang","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672044"},{"key":"ref38","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"},{"issue":"43","key":"ref39","first-page":"1","article-title":"Benchmarking graph neural networks","volume":"24","author":"Dwivedi","year":"2023","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"ref40","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","volume":"28","author":"Pascanu","year":"2013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2449"},{"key":"ref42","first-page":"10041","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dao","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1364\/AO.26.004972"},{"key":"ref44","first-page":"161","article-title":"The pagerank citation ranking: Bringing order to the web","volume-title":"Proc. 7th Int. World Wide Web Conf.","author":"Page","year":"1998"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0708838104"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/1097-461X(2001)81:1<29::AID-QUA6>3.0.CO;2-Y"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17283"},{"key":"ref48","first-page":"15734","article-title":"Nested graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang","year":"2021"},{"key":"ref49","first-page":"16138","article-title":"Adaptive universal generalized pagerank graph neural network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien","year":"2021"},{"key":"ref50","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kreuzer","year":"2021"},{"key":"ref51","first-page":"23321","article-title":"Graph inductive biases in transformers without message passing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"ref53","first-page":"10683","article-title":"Sign and basis invariant networks for spectral graph representation learning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lim","year":"2022"},{"key":"ref54","first-page":"3391","article-title":"Deep sets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Zaheer","year":"2017"},{"key":"ref55","first-page":"45657","article-title":"On the stability of expressive positional encodings for graph neural networks","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Huang","year":"2024"},{"key":"ref56","first-page":"3469","article-title":"Structure-aware transformer for graph representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2022"},{"key":"ref57","first-page":"23341","article-title":"How powerful are spectral graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.6028\/jres.045.026"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827500366124"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45167-9_12"},{"key":"ref61","first-page":"5964","article-title":"Taming graph kernels with random features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Choromanski","year":"2023"},{"key":"ref62","first-page":"18954","article-title":"Polynormer: Polynomial-expressive graph transformer in linear time","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Deng","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1670"},{"key":"ref64","first-page":"29000","article-title":"Long range language modeling via gated state spaces","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Mehta","year":"2022"},{"key":"ref65","first-page":"12193","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Fu","year":"2022"},{"key":"ref66","article-title":"Recurrent distance filtering for graph representation learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Ding","year":"2024"},{"key":"ref67","article-title":"HeteGraph-mamba: Heterogeneous graph learning via selective state space model","author":"Pan","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2026.113197"},{"key":"ref69","first-page":"51635","article-title":"Learning long range dependencies on graphs via random walks","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Chen","year":"2025"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599256"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3023"},{"key":"ref72","first-page":"64377","article-title":"Does graph prompt work? A data operation perspective with theoretical analysis","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Wang","year":"2025"},{"key":"ref73","first-page":"23733","article-title":"From stars to subgraphs: Uplifting any GNN with local structure awareness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2021"},{"key":"ref74","first-page":"25446","article-title":"Boosting the cycle counting power of graph neural networks with i$^{2}$2-GNNs","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Huang","year":"2022"},{"key":"ref75","first-page":"40","article-title":"A large-scale database for graph representation learning","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Freitas","year":"2021"},{"key":"ref76","article-title":"Residual gated graph convNets","author":"Bresson","year":"2017"},{"key":"ref77","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Corso","year":"2020"},{"key":"ref78","first-page":"35433","article-title":"Specformer: Spectral graph neural networks meet transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Bo","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2275"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/11595778\/11474332-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11474332.pdf?arnumber=11474332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:37Z","timestamp":1783453477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11474332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":79,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3680437","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":[[2026,8]]}}}