{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:02:43Z","timestamp":1780444963134,"version":"3.54.1"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,28]]},"DOI":"10.1109\/sbac-pad66369.2025.00024","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:39:34Z","timestamp":1764787174000},"page":"168-179","source":"Crossref","is-referenced-by-count":1,"title":["Accelerating GNN Inference via Automated Parallel Execution on Edge Heterogeneous Platforms"],"prefix":"10.1109","author":[{"given":"Yi-Chien","family":"Lin","sequence":"first","affiliation":[{"name":"University of Southern California (USC),Los Angeles,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyang","family":"Fan","sequence":"additional","affiliation":[{"name":"University of Southern California (USC),Los Angeles,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameh","family":"Gobriel","sequence":"additional","affiliation":[{"name":"Intel Labs,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nilesh","family":"Jain","sequence":"additional","affiliation":[{"name":"Intel Labs,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktor K.","family":"Prasanna","sequence":"additional","affiliation":[{"name":"University of Southern California (USC),Los Angeles,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389268"},{"key":"ref2","article-title":"Retrieval-augmented generation for code summarization via hybrid gnn","author":"Liu","year":"2021"},{"key":"ref3","article-title":"Gnn is a counter\u0192 revisiting gnn for question answering","author":"Wang","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.45"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01973"},{"key":"ref6","article-title":"Overlapping community detection with graph neural networks","author":"Shchur","year":"2019"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.14778\/3352063.3352127","article-title":"Aligraph: A comprehensive graph neural network platform","author":"Zhu","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10664946"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10665193"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC55918.2022.00017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01226-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3226481"},{"key":"ref14","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"International Conference on Learning Representations","author":"Kipf"},{"key":"ref15","article-title":"Inductive representation learning on large graphs","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Hamilton"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00040"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502359"},{"key":"ref19","article-title":"Graph analytics on modern massively parallel systems","author":"Vella","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00104"},{"key":"ref21","article-title":"Core ml tools [online]"},{"key":"ref22","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2024.3371332"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"ref26","volume-title":"A microarchitectural study on apple\u2019s a11 bionic processor","author":"Banerjee","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575725"},{"key":"ref29","article-title":"Gpipe: efficient training of giant neural networks using pipeline parallelism","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Huang"},{"key":"ref30","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"ref32","article-title":"Graph-SAINT: Graph sampling based inductive learning method","volume-title":"International Conference on Learning Representations","author":"Zeng"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1142\/4918"},{"key":"ref34","article-title":"Fast graph representation learning with PyTorch Geometric","author":"Fey","year":"2019","journal-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3460352"},{"key":"ref36","article-title":"Introduction to the xe-hpg architecture [white paper]","year":"2021"},{"key":"ref37","article-title":"Open graph benchmark: Datasets for machine learning on graphs","author":"Hu","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM51124.2021.00012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref40","article-title":"Quiver: Supporting gpus for low-latency, high-throughput gnn serving with workload awareness","author":"Tan","year":"2023"},{"key":"ref41","article-title":"Ryzen ai software [online]"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1145\/1854273.1854322","article-title":"The paralax infrastructure: automatic parallelization with a helping hand","volume-title":"Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques","author":"Vandierendonck"},{"key":"ref43","article-title":"Alpa: Automating inter-and {Intra-Operator} parallelism for distributed deep learning","author":"Zheng","year":"2022","journal-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/71.993206"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2004.1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ROSS51935.2020.00011"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1810479.1810498"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.01.001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.57"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01209-9_23"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1999.760523"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CCGridW59191.2023.00084"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413854"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624753"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED54688.2022.9806197"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546129"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00356-5"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2021.3087707"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530572"}],"event":{"name":"2025 IEEE\/SBC 37th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","location":"Bonito, Mato Grosso do Sul, Brazil","start":{"date-parts":[[2025,10,28]]},"end":{"date-parts":[[2025,10,31]]}},"container-title":["2025 IEEE\/SBC 37th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11264602\/11264604\/11264683.pdf?arnumber=11264683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:50:14Z","timestamp":1764834614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/sbac-pad66369.2025.00024","relation":{},"subject":[],"published":{"date-parts":[[2025,10,28]]}}}