{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T12:05:26Z","timestamp":1779883526376,"version":"3.53.1"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems Architecture"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.sysarc.2026.103829","type":"journal-article","created":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T22:56:44Z","timestamp":1777762604000},"page":"103829","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RAP: A reliability-aware pruning framework for deep neural networks"],"prefix":"10.1016","volume":"176","author":[{"given":"Setareh","family":"Ahsaei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohsen","family":"Raji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Behnam","family":"Ghavami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.sysarc.2026.103829_bib0001","article-title":"An overview of vision transformers for image processing: a survey","volume":"14","author":"Kameswari","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"issue":"7","key":"10.1016\/j.sysarc.2026.103829_bib0002","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1162\/neco_a_01764","article-title":"A survey on artificial neural networks in Human\u2014Robot interaction","volume":"37","author":"Swietlicka","year":"2025","journal-title":"Neural. Comput."},{"issue":"3","key":"10.1016\/j.sysarc.2026.103829_bib0003","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/s10462-024-11033-5","article-title":"Edge deep learning in computer vision and medical diagnostics: a comprehensive survey","volume":"58","author":"Xu","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.sysarc.2026.103829_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126227","article-title":"Do we really need a new theory to understand over-parameterization?","volume":"543","author":"Oneto","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.sysarc.2026.103829_bib0005","article-title":"SAViT: structure-Aware vision transformer pruning via collaborative optimization","author":"Zheng","year":"2022"},{"issue":"1","key":"10.1016\/j.sysarc.2026.103829_bib0006","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s10791-024-09463-4","article-title":"Towards compressed and efficient CNN architectures via pruning","volume":"27","author":"Narkhede","year":"2024","journal-title":"Discov. Comput."},{"key":"10.1016\/j.sysarc.2026.103829_bib0007","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"X-Pruner: eXplainable pruning for vision transformers","author":"Yu","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103829_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106220","article-title":"ARPruning: an automatic channel pruning based on attention map ranking","volume":"174","author":"Yuan","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.sysarc.2026.103829_bib0009","series-title":"Proceedings of the 29th IEEE European Test Symposium","first-page":"2024","article-title":"Cross-layer reliability analysis of nvdla accelerators: exploring the configuration space","author":"Veronesi","year":"2024"},{"issue":"23\u201324","key":"10.1016\/j.sysarc.2026.103829_bib0010","article-title":"A comprehensive soft error resiliency analysis of distributed deep neural networks","volume":"37","author":"Ahsaei","year":"2025","journal-title":"Concurr. Comput."},{"key":"10.1016\/j.sysarc.2026.103829_bib0011","series-title":"Proceedings - Design Automation Conference","article-title":"DRIS-3: deep neural network reliability improvement scheme in 3D die-stacked memory based on fault analysis","author":"Kim","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103829_bib0012","series-title":"33rd IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2020","article-title":"Reliability evaluation of pruned neural networks against errors on parameters","author":"Gao","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103829_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.microrel.2022.114498","article-title":"Reliability evaluation of FPGA based pruned neural networks","volume":"130","author":"Gao","year":"2022","journal-title":"Microelectron. Reliab."},{"key":"10.1016\/j.sysarc.2026.103829_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2024.103242","article-title":"Evaluating single event upsets in deep neural networks for semantic segmentation: an embedded system perspective","volume":"154","author":"Guti\u00e9rrez-Zaballa","year":"2024","journal-title":"J. Syst. Architect."},{"key":"10.1016\/j.sysarc.2026.103829_bib0015","series-title":"2022 12th International Conference on Computer and Knowledge Engineering, ICCKE","article-title":"GAP: fault tolerance improvement of convolutional Neural networks through GAN-aided pruning","volume":"2022","author":"Hosseinzadeh","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103829_bib0016","doi-asserted-by":"crossref","unstructured":"J.Y. Hong, S. Kim, J.W. Jang, and J.S. Yang, \u201cLOCo: LPDDR optimization with compression and IECC scheme for DNN inference,\u201d in Proceedings of the 29th International Symposium on Low Power Electronics and Design, ISLPED 2024, 2024. doi: 10.1145\/3665314.3670812.","DOI":"10.1145\/3665314.3670812"},{"key":"10.1016\/j.sysarc.2026.103829_bib0017","series-title":"2024 IEEE 30th International Symposium on On-Line Testing and Robust System Design (IOLTS)","first-page":"1","article-title":"Cost-effective fault tolerance for cnns using parameter vulnerability based hardening and pruning","author":"Ahmadilivani","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103829_bib0018","article-title":"LOST-ViT: a low overhead soft error tolerance framework for vision transformers via model compression and selective bit-level redundancy","author":"Ahsaei","year":"2025","journal-title":"J. Syst. Architect."},{"key":"10.1016\/j.sysarc.2026.103829_bib0019","article-title":"Recall distortion in neural network pruning and the undecayed pruning algorithm","author":"Good","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103829_bib0020","series-title":"2024 25th International Symposium on Quality Electronic Design (ISQED)","first-page":"1","article-title":"Exploration of activation fault reliability in quantized systolic array-based dnn accelerators","author":"Taheri","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103829_bib0021","series-title":"Proceedings of Machine Learning Research","article-title":"The combinatorial brain surgeon: pruning weights that cancel one another in neural networks","author":"Yu","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103829_bib0022","doi-asserted-by":"crossref","DOI":"10.1145\/3624476","article-title":"Surrogate lagrangian relaxation: a path to retrain-free deep neural network pruning","author":"Zhou","year":"2023","journal-title":"ACM Trans. Des. Autom. Electron. Syst."},{"key":"10.1016\/j.sysarc.2026.103829_bib0023","series-title":"Proceedings of the IEEE VLSI Test Symposium","article-title":"Special session: approximation and fault resiliency of DNN accelerators","author":"Ahmadilivani","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103829_bib0024","doi-asserted-by":"crossref","DOI":"10.1002\/stvr.1873","article-title":"Investigating the impact of transient hardware faults on deep learning neural network inference","author":"Rahman","year":"2024","journal-title":"Softw. Test. Verific. Reliab."},{"issue":"6","key":"10.1016\/j.sysarc.2026.103829_bib0025","doi-asserted-by":"crossref","DOI":"10.1145\/3638242","article-title":"A systematic literature review on hardware reliability assessment methods for Deep neural networks","volume":"56","author":"Ahmadilivani","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.sysarc.2026.103829_bib0026","article-title":"Error resilience in deep neural networks using neuron gradient statistics","author":"Amarnath","year":"2023","journal-title":"IEEE Trans. Comput.-Aided Design Integr. Circu. Syst."},{"key":"10.1016\/j.sysarc.2026.103829_bib0027","series-title":"Proceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022","article-title":"Estimating vulnerability of all model parameters in DNN with a small number of fault injections","author":"Zhang","year":"2022"},{"issue":"3","key":"10.1016\/j.sysarc.2026.103829_bib0028","article-title":"Improving deep neural network reliability via transient-fault-aware design and training","volume":"13","author":"Dos Santos","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"10.1016\/j.sysarc.2026.103829_bib0029","series-title":"Proceedings - 2025 IEEE 3rd International Conference on Mobility, Operations, Services and Technologies, MOST","article-title":"Better reliability compression: model pruning with calibrated uncertainty estimation for mobile deep learning applications","volume":"2025","author":"Ma","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103829_bib0030","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"DeepCompress-ViT: rethinking model compression to enhance efficiency of vision transformers at the edge","author":"Ahmed","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103829_bib0031","series-title":"European Conference on Computer Vision","first-page":"152","article-title":"Pruning by explaining revisited: optimizing attribution methods to prune cnns and transformers","author":"Hatefi","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103829_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2210","article-title":"Prune efficiently by soft pruning","author":"Agarwal","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103829_bib0033","doi-asserted-by":"crossref","DOI":"10.1017\/S0962492922000101","article-title":"Floating-point arithmetic","volume":"32","author":"Boldo","year":"2023","journal-title":"Acta Numerica"},{"key":"10.1016\/j.sysarc.2026.103829_bib0034","series-title":"Proceedings of the International Joint Conference on Neural Networks","article-title":"FAQ: mitigating the impact of faults in the weight memory of DNN accelerators through fault-aware quantization","author":"Hanif","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103829_bib0035","series-title":"2024 IEEE Conference on Artificial Intelligence (CAI)","first-page":"747","article-title":"Is complexity required for neural network pruning? A case study on global magnitude pruning","author":"Gupta","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103829_bib0036","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2022.3182659","article-title":"Methods for pruning deep neural networks","volume":"10","author":"Vadera","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.sysarc.2026.103829_bib0037","doi-asserted-by":"crossref","unstructured":"M. Rogenmoser et al., \u201cDesign and experimental investigation of trikarenos: a fault-tolerant 28nm risc-v-based soc,\u201d in RADECS 2024, 2024.","DOI":"10.1109\/TNS.2025.3564739"},{"key":"10.1016\/j.sysarc.2026.103829_bib0038","article-title":"Neutron-indced effects on a self-refresh DRAM","volume":"128","author":"Matana Luza","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103829_bib0039","series-title":"IEEE International Reliability Physics Symposium Proceedings","article-title":"Thermal-neutron SER mitigation by cobalt-contact in 7 nm bulk-FinFET technology","author":"Uemura","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103829_bib0040","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3447085","article-title":"A survey on deep neural network pruning: taxonomy, comparison, analysis, and recommendations","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.sysarc.2026.103829_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127280","article-title":"Sparse optimization guided pruning for neural networks","volume":"574","author":"Shi","year":"2024","journal-title":"Neurocomputing"},{"issue":"8","key":"10.1016\/j.sysarc.2026.103829_bib0042","doi-asserted-by":"crossref","DOI":"10.1109\/TAI.2024.3366497","article-title":"Distilled gradual pruning with pruned fine-tuning","volume":"5","author":"Fontana","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.sysarc.2026.103829_bib0043","series-title":"2020 IEEE 11th Latin American Symposium on Circuits and Systems, LASCAS","article-title":"Reliability evaluation of compressed deep learning models","author":"Goldstein","year":"2020"}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001475?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001475?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:13:14Z","timestamp":1779880394000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1383762126001475"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":43,"alternative-id":["S1383762126001475"],"URL":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103829","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RAP: A reliability-aware pruning framework for deep neural networks","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems Architecture","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103829","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103829"}}