{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T07:10:12Z","timestamp":1737443412872,"version":"3.33.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFC3303800"],"award-info":[{"award-number":["2023YFC3303800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,6]]},"DOI":"10.1109\/smc54092.2024.10831406","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:20Z","timestamp":1737398360000},"page":"1036-1041","source":"Crossref","is-referenced-by-count":0,"title":["Efficient One-Shot Pruning of Large Language Models with Low-Rank Approximation"],"prefix":"10.1109","author":[{"given":"Yangyan","family":"Xu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangfang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongxin","family":"Mi","sequence":"additional","affiliation":[{"name":"National Computer Network Emergency Response Technical Team\/Coordination Center of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nannan","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dakui","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Opt: Open pre-trained trans-former language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Are emergent abilities of large language models a mirage?","author":"Schaeffer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-35995-8_39"},{"key":"ref5","first-page":"119","article-title":"Metabert: Collaborative meta-learning for accelerating bert infer-ence","volume-title":"2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE","author":"Xu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448403"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8148-9_5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63749-0_13"},{"key":"ref9","article-title":"A survey on model com-pression for large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"10323","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","volume-title":"International Conference on Machine Learning, ICML 2023","volume":"202","author":"Frantar"},{"key":"ref11","article-title":"A simple and effective pruning approach for large language models","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Get more with less: Synthesizing recurrence with kv cache compression for efficient llm inference","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"LIm-pruner: On the structural pruning of large language models","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"129","article-title":"What is the state of neural network pruning?","volume-title":"Proceedings of machine learning and systems","volume":"2","author":"Blalock"},{"key":"ref15","first-page":"15 834","article-title":"The lottery ticket hypothesis for pre-trained bert net-works","volume-title":"Advances in neural information processing systems","volume":"33","author":"Chen","year":"2020"},{"key":"ref16","first-page":"5958","article-title":"Train big, then compress: Rethinking model size for efficient training and inference of transformers","volume-title":"International Conference on machine learning","author":"Li"},{"key":"ref17","article-title":"Llm. int8 (): 8-bit matrix multiplication for transformers at scale","author":"Dettmers","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Optimal brain damage","volume":"2","author":"LeCun","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.188"},{"key":"ref21","first-page":"22 137","article-title":"Deja vu: Contextual sparsity for efficient llms at inference time","volume-title":"International Conference on Machine Learning. PMLR","author":"Liu"},{"key":"ref22","first-page":"10542","article-title":"Why random pruning is all we need to start sparse","volume-title":"International Conference on Machine Learning, ICML 2023, ser. Proceedings of Machine Learning Research","volume":"202","author":"Gadhikar"},{"key":"ref23","article-title":"Sparsity may cry: Let us fail (current) sparse neural networks together!","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"17402","article-title":"Outlier suppression: Pushing the limit of low-bit trans-former language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Quantease: Optimization-based quantization for language models-an efficient and intuitive algorithm","author":"Behdin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Awq: Activation-aware weight quantization for llm compression and accel-eration","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Spqr: A sparse-quantized representation for near-lossless llm weight compression","author":"Dettmers","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"6726","article-title":"Spdy: Accurate pruning with speedup guarantees","volume-title":"International Conference on Machine Learning, 2022","author":"Frantar"},{"key":"ref29","first-page":"24101","article-title":"A fast post-training pruning framework for transformers","volume":"35","author":"Kwon","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"21099","article-title":"Accelerated sparse neural training: A provable and efficient method to find n: m transposable masks","volume":"34","author":"Hubara","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"18098","article-title":"Woodfisher: Efficient second-order approximation for neural network compression","volume":"33","author":"Singh","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","first-page":"4475","article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","volume":"35","author":"Frantar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","article-title":"Accelerating sparse deep neural net-works","author":"Mishra","year":"2021","journal-title":"arXiv preprint"},{"article-title":"Lora: Low-rank adaptation of large language models","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, 2022.","author":"Hu","key":"ref34"},{"key":"ref35","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv preprint"},{"journal-title":"Version v0. 0.1. Sept, 2021.","article-title":"A framework for few-shot language model evaluation","author":"Gao","key":"ref36"},{"key":"ref37","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref38","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"}],"event":{"name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2024,10,6]]},"location":"Kuching, Malaysia","end":{"date-parts":[[2024,10,10]]}},"container-title":["2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830919\/10830920\/10831406.pdf?arnumber=10831406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:32:09Z","timestamp":1737441129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10831406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/smc54092.2024.10831406","relation":{},"subject":[],"published":{"date-parts":[[2024,10,6]]}}}