{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:47:44Z","timestamp":1771922864690,"version":"3.50.1"},"reference-count":67,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/cgo68049.2026.11395219","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:46:32Z","timestamp":1771879592000},"page":"14-27","source":"Crossref","is-referenced-by-count":0,"title":["GRANII: Selection and Ordering of Primitives in GRAph Neural Networks using Input Inspection"],"prefix":"10.1109","author":[{"given":"Damitha","family":"Lenadora","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vimarsh","family":"Sathia","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerasimos","family":"Gerogiannis","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serif","family":"Yesil","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josep","family":"Torrellas","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charith","family":"Mendis","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5171","article-title":"Link prediction based on graph neural networks","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Zhang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331372"},{"key":"ref4","article-title":"Learning multimodal graph-to-graph translation for molecule optimization","volume-title":"International Conference on Learning Representations","author":"Jin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00628"},{"key":"ref6","first-page":"387","article-title":"A learned performance model for tensor processing units","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Kaufman"},{"key":"ref7","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2020"},{"key":"ref8","article-title":"Fast graph representation learning with pytorch geometric","author":"Fey","year":"2019"},{"key":"ref9","first-page":"443","article-title":"NeuGraph: Parallel deep neural network computation on large graphs","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Ma"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650063"},{"key":"ref11","first-page":"515","article-title":"Graphiler: Optimizing graph neural networks with message passing data flow graph","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Xie"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456247"},{"key":"ref13","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with roc","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Jia"},{"key":"ref14","first-page":"495","article-title":"Dorylus: Affordable, scalable, and accurate GNN training with distributed CPU servers and serverless threads","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Thorpe"},{"key":"ref15","first-page":"467","article-title":"Understanding gnn computational graph: A coordinated computation, io, and memory perspective","volume":"4","author":"Zhang","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441585"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/lca.2020.2970395"},{"key":"ref18","first-page":"515","article-title":"GNNAdvisor: An adaptive and efficient runtime system for GNN acceleration on GPUs","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Wang"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/978-3-030-99372-6_7","article-title":"Optimizing sparse matrix multiplications for graph neural networks","volume-title":"Languages and Compilers for Parallel Computing","author":"Qiu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575723"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523442"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3626183.3659985"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1145\/3689730","article-title":"Sparseauto: An auto-scheduler for sparse tensor computations using recursive loop nest restructuring","author":"Dias","year":"2024"},{"key":"ref24","article-title":"How powerful are graph neural networks?","volume-title":"International Conference on Learning Representations","author":"Xu"},{"key":"ref25","article-title":"Graph attention networks","volume-title":"International Conference on Learning Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref26","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Hamilton"},{"key":"ref27","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"ref28","article-title":"Topology adaptive graph convolutional networks","author":"Du","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3322125"},{"key":"ref30","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"CoRR","author":"Kipf","year":"2016"},{"key":"ref31","article-title":"Automatic differentiation in pytorch","author":"Paszke","year":"2017"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178495"},{"key":"ref34","first-page":"126170","article-title":"Multi-view brain network classification based on adaptive graph isomorphic information bottleneck mamba","volume-title":"Expert Systems with Applications","volume":"267","author":"Dong","year":"2025"},{"key":"ref35","first-page":"122520","article-title":"A graph attention network framework for generalized-horizon multi-plant solar power generation forecasting using heterogeneous data","volume-title":"Renewable Energy","volume":"243","author":"Hasnat","year":"2025"},{"key":"ref36","first-page":"112048","article-title":"Model interpretation and interpretability performance evaluation of graph convolutional network fault diagnosis for air handling units","volume-title":"Journal of Building Engineering","volume":"103","author":"Li","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-024-01656-7"},{"key":"ref38","article-title":"Neuroback: Improving cdcl sat solving using graph neural networks","author":"Wang","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ase56229.2023.00167"},{"key":"ref40","article-title":"A critical look at the evaluation of gnns under heterophily: Are we really making progress?","author":"Platonov","year":"2024"},{"key":"ref41","article-title":"Position: Graph learning will lose relevance due to poor benchmarks","author":"Bechler-Speicher","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00366-x"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1101\/2022.05.16.491112","article-title":"Topology adaptive graph convolution network with heterogeneous entities for predicting adverse events from drug-drug-interactions","volume-title":"bioRxiv","author":"Bagchi","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2025.3527694"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710881"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref47","article-title":"Open graph benchmark: datasets for machine learning on graphs","author":"Hu","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3459408"},{"key":"ref49","article-title":"Learning on large-scale text-attributed graphs via variational inference","author":"Zhao","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata52589.2021.9671372"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3584945"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575742"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126936"},{"key":"ref55","article-title":"Vectorizing sparse matrix computations with partially-strided codelets","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Cheshmi"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577506"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref58","article-title":"Speeding up spmv for power-law graph analytics by enhancing locality & vectorization","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Yesil"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295716"},{"issue":"6","key":"ref60","first-page":"1473","article-title":"Freshgnn: Reducing memory access via stable historical embeddings for graph neural network training","volume-title":"Proc. VLDB Endow","volume":"17","author":"Huang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps49936.2021.00034"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527403"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607097"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3656445"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3591236"}],"event":{"name":"2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11395173\/11394837\/11395219.pdf?arnumber=11395219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:42:30Z","timestamp":1771918950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11395219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/cgo68049.2026.11395219","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}