{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:39:03Z","timestamp":1772933943751,"version":"3.50.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402115","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Degree-Based Scheduling and Memory Management for Large-Scale Exact Online GNN Inference"],"prefix":"10.1109","author":[{"given":"Alireza","family":"Namazi","sequence":"first","affiliation":[{"name":"University of Virginia"}]},{"given":"Haiying","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Virginia"}]},{"given":"Tanmoy","family":"Sen","sequence":"additional","affiliation":[{"name":"University of Virginia"}]},{"given":"Minjia","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","author":"Kipf","year":"2016","journal-title":"Semi-supervised classification with graph convolutional networks"},{"issue":"20","key":"ref3","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"stat"},{"key":"ref4","author":"Frasca","year":"2020","journal-title":"Sign: Scalable inception graph neural networks"},{"key":"ref5","article-title":"Link prediction based on graph neural networks","volume":"31","author":"Zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570407"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557356"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474379"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401253"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.066"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3076974"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105020"},{"key":"ref15","author":"Tan","year":"2023","journal-title":"Quiver: Supporting gpus for low-latency, high-throughput gnn serving with workload awareness"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00084"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486993"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00019"},{"key":"ref19","first-page":"172","article-title":"Accelerating training and inference of graph neural networks with fast sampling and pipelining","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Kaler","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00248"},{"key":"ref21","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","volume-title":"ICLR workshop on representation learning on graphs and manifolds","author":"Wang","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3107250"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/316194.316229"},{"key":"ref25","first-page":"17","article-title":"Powergraph: distributed graph-parallel computation on natural graphs","volume-title":"10th USENIX symposium on operating systems design and implementation (OSDI 12)","author":"Gonzalez","year":"2012"},{"key":"ref26","article-title":"Gsm","year":"2025","journal-title":"Anon."},{"key":"ref27","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"International conference on machine learning","author":"Gilmer","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519557"},{"key":"ref30","first-page":"551","article-title":"P3: Distributed deep graph learning at scale","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Gandhi","year":"2021"},{"key":"ref31","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2350190.2350193"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577528"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551819"},{"key":"ref35","first-page":"117","article-title":"Taming throughput-latency tradeoff in 11 m inference with sarathi-serve","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal","year":"2024"},{"key":"ref36","first-page":"663","article-title":"Alpaserve: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599805"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2024.3351282"},{"key":"ref39","author":"Chen","year":"2025","journal-title":"Deal: Distributed end-to-end gnn inference for all nodes"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/icde60146.2024.00236"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC56025.2022.00045"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.14778\/3461535.3461547"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710854"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-8135-9_6"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1145\/3489517.3530503","article-title":"Gnnie: Gnn inference engine with load-balancing and graph-specific caching","volume-title":"Proceedings of the 59th ACM\/IEEE Design Automation Conference","author":"Mondal","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071015"},{"key":"ref47","first-page":"443","article-title":"Serving dnns like clockwork: Performance predictability from the bottom up","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati","year":"2020"},{"key":"ref48","first-page":"539","article-title":"Microsecond-scale preemption for concurrent gpu-accelerated dnn inferences","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"ref50","first-page":"1403","article-title":"Cassini: Network-aware job scheduling in machine learning clusters","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Rajasekaran","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"ref52","article-title":"$s$ 3: Increasing gpu utilization during generative inference for higher throughput","volume":"36","author":"Jin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","author":"Wu","year":"2023","journal-title":"Fast distributed inference serving for large language models"},{"key":"ref54","article-title":"Response length perception and sequence scheduling: An 11 m -empowered 11 m inference pipeline","volume":"36","author":"Zheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402115.pdf?arnumber=11402115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:55:53Z","timestamp":1772866553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402115","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}