{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:04:48Z","timestamp":1790111088738,"version":"4.0.1"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872422"],"award-info":[{"award-number":["61872422"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109394","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T23:31:06Z","timestamp":1784244666000},"page":"109394","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["An intelligent sparse approximate inverse selection method based on convolutional neural networks"],"prefix":"10.1016","volume":"205","author":[{"given":"Xinghe","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ru","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8079-3172","authenticated-orcid":false,"given":"Yige","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109394_bib0001","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.parco.2017.05.006","article-title":"Preconditioned Krylov solvers on GPUs","volume":"68","author":"Anzt","year":"2017","journal-title":"Parallel Computing"},{"issue":"1","key":"10.1016\/j.neunet.2026.109394_bib0002","doi-asserted-by":"crossref","first-page":"C53","DOI":"10.1137\/15M1027826","article-title":"A factored sparse approximate inverse preconditioned conjugate gradient solver on graphics processing units","volume":"38","author":"Bernaschi","year":"2016","journal-title":"SIAM Journal on Scientific Computing"},{"issue":"3","key":"10.1016\/j.neunet.2026.109394_bib0003","doi-asserted-by":"crossref","first-page":"C139","DOI":"10.1137\/18M1197461","article-title":"A dynamic pattern factored sparse approximate inverse preconditioner on graphics processing units","volume":"41","author":"Bernaschi","year":"2019","journal-title":"SIAM Journal on Scientific Computing"},{"key":"10.1016\/j.neunet.2026.109394_bib0004","doi-asserted-by":"crossref","unstructured":"Carson, E. C., & Khan, N. (2023). Mixed precision iterative refinement with sparse approximate inverse preconditioning. SIAM Journal on Scientific Computing, 45(3), C131\u2013C153.","DOI":"10.1137\/22M1487709"},{"issue":"3","key":"10.1016\/j.neunet.2026.109394_bib0005","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis"},{"issue":"3","key":"10.1016\/j.neunet.2026.109394_bib0006","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1109\/TPDS.2014.2312199","article-title":"GPU-accelerated sparse LU factorization for circuit simulation with performance modeling","volume":"26","author":"Chen","year":"2014","journal-title":"IEEE Transactions on Parallel and Distributed"},{"key":"10.1016\/j.neunet.2026.109394_bib0007","series-title":"Proc. 15th ACM SIGPLAN symp. Principles and practice of parallel programming (PPoPP\u201910)","first-page":"9","article-title":"Model-driven autotuning of sparse matrix-vector multiply on GPUs","author":"Choi","year":"2010"},{"issue":"1","key":"10.1016\/j.neunet.2026.109394_bib0008","first-page":"1","article-title":"The university of florida sparse matrix collection","volume":"38","author":"Davis","year":"2011","journal-title":"ACM Transactions on Mathematical Software"},{"issue":"9","key":"10.1016\/j.neunet.2026.109394_bib0009","doi-asserted-by":"crossref","first-page":"1852","DOI":"10.1109\/TPDS.2012.286","article-title":"Parallel sparse approximate inverse preconditioning on graphic processing units","volume":"24","author":"Dehnavi","year":"2013","journal-title":"IEEE Transactions on Parallel and Distributed"},{"issue":"4","key":"10.1016\/j.neunet.2026.109394_bib0010","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1137\/S0895479897317788","article-title":"Scalable parallel preconditioning with the sparse approximate inverse of triangular systems","volume":"20","author":"Duin","year":"1999","journal-title":"SIAM Journal on Matrix Analysis and Applications"},{"key":"10.1016\/j.neunet.2026.109394_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.parco.2020.102724","article-title":"A thread-adaptive sparse approximate inverse preconditioning algorithm on multi-GPUs","volume":"101","author":"Gao","year":"2021","journal-title":"Parallel Computing"},{"issue":"2","key":"10.1016\/j.neunet.2026.109394_bib0012","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2Net: A new multi-scale backbone architecture","volume":"43","author":"Gao","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis"},{"issue":"5","key":"10.1016\/j.neunet.2026.109394_bib0013","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1109\/TPDS.2013.123","article-title":"A performance modeling and optimization analysis tool for sparse matrix-vector multiplication on GPUs","volume":"25","author":"Guo","year":"2014","journal-title":"IEEE Transactions on Parallel and Distributed"},{"issue":"7","key":"10.1016\/j.neunet.2026.109394_bib0014","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.5598","article-title":"An efficient sparse approximate inverse preconditioning algorithm on GPU","volume":"32","author":"He","year":"2020","journal-title":"Concurrency and Computation- Practice and Experience"},{"issue":"3","key":"10.1016\/j.neunet.2026.109394_bib0015","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1109\/TVLSI.2015.2421287","article-title":"GPU-accelerated parallel sparse LU factorization method for fast circuit analysis","volume":"24","author":"He","year":"2016","journal-title":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems"},{"key":"10.1016\/j.neunet.2026.109394_bib0016","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109394_bib0017","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109394_bib0018","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"issue":"2","key":"10.1016\/j.neunet.2026.109394_bib0019","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1177\/10943420211017188","article-title":"A GPU-accelerated adaptive FSAI preconditioner for massively parallel simulations","volume":"36","author":"Isotton","year":"2022","journal-title":"International Journal of High Performance Computing"},{"issue":"4","key":"10.1016\/j.neunet.2026.109394_bib0020","doi-asserted-by":"crossref","first-page":"1244","DOI":"10.21105\/joss.01244","article-title":"The suitesparse matrix collection website interface","volume":"35","author":"Kolodziej","year":"2019","journal-title":"Journal of Open Source Software"},{"key":"10.1016\/j.neunet.2026.109394_bib0021","series-title":"Proceedings of 26th annual conference on neural information processing systems","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"vol. 2","author":"Krizhevsky","year":"2012"},{"key":"10.1016\/j.neunet.2026.109394_bib0022","series-title":"Proceedings of the 33th ACM international symposium on high-performance parallel and distributed computing","first-page":"251","article-title":"Extending sparse patterns to improve inverse preconditioning on GPU architectures","author":"Laut","year":"2024"},{"issue":"11","key":"10.1016\/j.neunet.2026.109394_bib0023","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"10.1016\/j.neunet.2026.109394_bib0024","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1109\/TPDS.2014.2308221","article-title":"Performance analysis and optimization for SpMV on GPU using probabilistic modeling","volume":"26","author":"Li","year":"2015","journal-title":"IEEE Transactions on Parallel and Distributed"},{"key":"10.1016\/j.neunet.2026.109394_bib0025","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11976","article-title":"A convNet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109394_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.compfluid.2025.106846","article-title":"Optimized workload distribution for GPU-accelerated combustion simulations in heterogeneous CPU-GPU architectures","volume":"302","author":"Moure","year":"2025","journal-title":"Computers & Fluids"},{"issue":"5","key":"10.1016\/j.neunet.2026.109394_bib0027","doi-asserted-by":"crossref","first-page":"S602","DOI":"10.1137\/140980260","article-title":"Amgx: A library for GPU accelerated algebraic multigrid and preconditioned iterative methods","volume":"37","author":"Naumov","year":"2015","journal-title":"SIAM Journal on Scientific Computing"},{"key":"10.1016\/j.neunet.2026.109394_bib0028","series-title":"2018 IEEE international parallel and distributed processing symposium workshops","article-title":"Effective machine learning based format selection and performance modeling for SpMV on GPUs","author":"Nisa","year":"2018"},{"key":"10.1016\/j.neunet.2026.109394_bib0029","unstructured":"NVIDIA (2024). CUDA C programming guide.V12.7. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html."},{"key":"10.1016\/j.neunet.2026.109394_bib0030","unstructured":"NVIDIA (2025). cuDNN library, v.9.16.0. https:\/\/developer.nvidia.com\/cudnn-downloads."},{"issue":"5","key":"10.1016\/j.neunet.2026.109394_bib0031","doi-asserted-by":"crossref","first-page":"S412","DOI":"10.1137\/15M1026419","article-title":"ViennaCL\u2014linear algebra library for multi- and many-core architectures","volume":"38","author":"Rupp","year":"2016","journal-title":"SIAM Journal on Scientific Computing"},{"key":"10.1016\/j.neunet.2026.109394_bib0032","series-title":"Iterative methods for sparse linear systems","author":"Saad","year":"2003"},{"key":"10.1016\/j.neunet.2026.109394_bib0033","series-title":"Proceedings of the 29th ACM on international conference on supercomputing","first-page":"99","article-title":"Automatic selection of sparse matrix representation on GPUs","author":"Sedaghati","year":"2015"},{"key":"10.1016\/j.neunet.2026.109394_bib0034","series-title":"Proceedings of 3rd international conference on learning representations","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"10.1016\/j.neunet.2026.109394_bib0035","series-title":"2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"5686","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2019"},{"key":"10.1016\/j.neunet.2026.109394_bib0036","series-title":"Proceedings of the IEEE computer society conference on computer vision and pattern recognition","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"10.1016\/j.neunet.2026.109394_bib0037","series-title":"Proceedings of the international conference on machine learning","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"issue":"2","key":"10.1016\/j.neunet.2026.109394_bib0038","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1145\/3584373","article-title":"A heterogeneous parallel computing approach optimizing SpTTM on CPU-GPU via GCN","volume":"10","author":"Wang","year":"2023","journal-title":"ACM Transactions on Parallel Computing"},{"key":"10.1016\/j.neunet.2026.109394_bib0039","article-title":"Iterative methods in GPU-resident linear solvers for nonlinear constrained optimization","volume":"123","author":"Wirydowicz","year":"2025","journal-title":"Parallel Computing"},{"key":"10.1016\/j.neunet.2026.109394_bib0040","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1492","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"10.1016\/j.neunet.2026.109394_bib0041","series-title":"Proceedings of the 23rd ACM SIGPLAN symposium on principles and practice of parallel programming","first-page":"1","article-title":"Bridging the gap between deep learning and sparse matrix format selection","author":"Zhao","year":"2018"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600852X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600852X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:08:12Z","timestamp":1790107692000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802600852X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":41,"alternative-id":["S089360802600852X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109394","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An intelligent sparse approximate inverse selection method based on convolutional neural networks","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109394","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109394"}}