{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:05:07Z","timestamp":1782389107927,"version":"3.54.5"},"reference-count":56,"publisher":"Informa UK Limited","issue":"1","license":[{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901436"],"award-info":[{"award-number":["61901436"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Connection Science"],"published-print":{"date-parts":[[2022,12,31]]},"DOI":"10.1080\/09540091.2021.2024510","type":"journal-article","created":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T14:59:00Z","timestamp":1642431540000},"page":"990-1004","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":9,"title":["Multi-distribution noise quantisation: an extreme compression scheme for transformer according to parameter distribution"],"prefix":"10.1080","volume":"34","author":[{"given":"Zaiyang","family":"Yu","sequence":"first","affiliation":[{"name":"Institute of Semiconductors, Chinese Academy of Sciences, Beijing, People's Republic of China"},{"name":"Cognitive Computing Technology Joint Laboratory, Wave Group, Beijing, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Li","sequence":"additional","affiliation":[{"name":"Center of Materials Science and Optoelectronics Engineering & School of Microelectronics, University of Chinese Academy of Sciences, Beijing, People's Republic of China"},{"name":"Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology, Beijing, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjun","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Semiconductors, Chinese Academy of Sciences, Beijing, People's Republic of China"},{"name":"Cognitive Computing Technology Joint Laboratory, Wave Group, Beijing, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"Cognitive Computing Technology Joint Laboratory, Wave Group, Beijing, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Haining","sequence":"additional","affiliation":[{"name":"School of Police Administration, People's Public Security University of China, Beijing, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2022,1,17]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108102"},{"key":"CIT0002","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.020"},{"key":"CIT0003","unstructured":"Bhandare, A., Sripathi, V., Karkada, D., Menon, V., Choi, S., Datta, K. & Saletore, V. (2019). Efficient 8-bit quantization of transformer neural machine language translation model. CoRR abs\/1906.00532. http:\/\/arxiv.org\/abs\/1906.00532"},{"key":"CIT0004","unstructured":"Bie, A., Venkitesh, B., Monteiro, J., Haidar, M. A. & Rezagholizadeh, M. (2019). Fully quantizing a simplified transformer for end-to-end speech recognition. CoRR abs\/1911.03604. http:\/\/arxiv.org\/abs\/1911.03604"},{"key":"CIT0005","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054724"},{"key":"CIT0006","doi-asserted-by":"publisher","DOI":"10.17265\/2159-5313\/2016.09.003"},{"key":"CIT0007","unstructured":"Brock, A., De, S., Smith, S. L. & Simonyan, K. (2021, July 18\u201324). High-performance large-scale image recognition without normalization. In M. Meila & T. Zhang (Eds.), Proceedings of the 38th International Conference on Machine Learning, ICML 2021, Virtual Event (Vol. 139, pp. 1059\u20131071). PMLR. http:\/\/proceedings.mlr.press\/v139\/brock21a.html"},{"key":"CIT0008","unstructured":"Carreira-Perpi\u00f1\u00e1n, M. \u00c1. & Idelbayev, Y. (2017). Model compression as constrained optimization, with application to neural nets. Part II: Quantization. CoRR abs\/1707.04319. http:\/\/arxiv.org\/abs\/1707.04319"},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.433"},{"key":"CIT0010","unstructured":"D\u00e9fossez, A., Adi, Y. & Synnaeve, G. (2021). Differentiable model compression via pseudo quantization noise. CoRR abs\/2104.09987. https:\/\/arxiv.org\/abs\/2104.09987"},{"key":"CIT0011","first-page":"759","author":"Dong X.","year":"2019","journal-title":"Advances in neural information processing systems 32: Annual conference on Neural Information Processing Systems"},{"key":"CIT0012","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.240"},{"key":"CIT0013","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.03.057"},{"key":"CIT0014","doi-asserted-by":"publisher","DOI":"10.17265\/2159-5313\/2016.09.003"},{"key":"CIT0015","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"CIT0016","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"CIT0017","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"CIT0018","doi-asserted-by":"publisher","DOI":"10.1109\/72.788654"},{"key":"CIT0019","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L. & Lewis, M. (2020, April 26\u201330). Generalization through memorization: Nearest neighbor language models. In 8th International Conference on Learning Representations, ICLR 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=HklBjCEKvH"},{"key":"CIT0020","unstructured":"Krause, B., Kahembwe, E., Murray, I. & Renals, S. (2019). Dynamic evaluation of transformer language models. CoRR abs\/1904.08378. http:\/\/arxiv.org\/abs\/1904.08378"},{"key":"CIT0021","unstructured":"Lee, J. H., Ha, S., Choi, S., Lee, W. & Lee, S. (2018). Quantization for rapid deployment of deep neural networks. CoRR abs\/1810.05488. http:\/\/arxiv.org\/abs\/1810.05488"},{"key":"CIT0022","unstructured":"Li, Y., Dong, X. & Wang, W. (2020, April 26\u201330). Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks. In 8th International Conference on Learning Representations, ICLR 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=BkgXT24tDS"},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"key":"CIT0024","unstructured":"Melis, G., Kocisk\u00fd, T. & Blunsom, P. (2020, April 26\u201330). Mogrifier LSTM. In 8th International Conference on Learning Representations, ICLR 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=SJe5P6EYvS"},{"key":"CIT0025","doi-asserted-by":"publisher","DOI":"10.17265\/2159-5313\/2016.09.003"},{"key":"CIT0026","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"CIT0027","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964838"},{"key":"CIT0028","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3032277"},{"key":"CIT0029","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.106"},{"key":"CIT0030","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3043026"},{"key":"CIT0031","first-page":"e6147","author":"Ning X.","year":"2020","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"CIT0032","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.388"},{"key":"CIT0033","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"CIT0034","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.1"},{"key":"CIT0035","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2021.102053"},{"key":"CIT0036","unstructured":"Riquelme, C., Puigcerver, J., Mustafa, B., Neumann, M., Jenatton, R., Pinto, A. S., Keysers, D. & Houlsby, N. (2021). Scaling vision with sparse mixture of experts. CoRR abs\/2106.05974. https:\/\/arxiv.org\/abs\/2106.05974"},{"key":"CIT0037","unstructured":"Santoro, A., Faulkner, R., Raposo, D., Rae, J. W., Chrzanowski, M., Weber, T., Wierstra, D., Vinyals, O., Pascanu, R. & Lillicrap, T. P. (2018). Relational recurrent neural networks. CoRR abs\/1806.01822. http:\/\/arxiv.org\/abs\/1806.01822"},{"key":"CIT0038","unstructured":"Simonyan, K. & Zisserman, A. (2015, May 7\u20139). Very deep convolutional networks for large-scale image recognition. In Y. Bengio & Y. LeCun (Eds.), 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"CIT0039","unstructured":"Stock, P., Fan, A., Graham, B., Grave, E., Gribonval, R., J\u00e9gou, H. & Joulin, A. (2021, May 3\u20137). Training with quantization noise for extreme model compression. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event. OpenReview.net. https:\/\/openreview.net\/forum?id=dV19Yyi1fS3"},{"key":"CIT0040","unstructured":"Stock, P., Joulin, A., Gribonval, R., Graham, B. & J\u00e9gou, H. (2020, April 26\u201330). And the bit goes down: Revisiting the quantization of neural networks. In 8th International Conference on Learning Representations, ICLR 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=rJehVyrKwH"},{"key":"CIT0041","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015074"},{"key":"CIT0042","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141. & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (pp. 5998\u20136008).\u00a0MIT Press."},{"key":"CIT0043","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2999492"},{"key":"CIT0044","unstructured":"Wang, C., Li, M. & Smola, A. J. (2019). Language models with transformers. arXiv preprint arXiv:1904.09408."},{"key":"CIT0045","unstructured":"Wang, D., Gong, C. & Liu, Q. (2019, June 9\u201315). Improving neural language modeling via adversarial training. In K. Chaudhuri & R. Salakhutdinov (Eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, CA, USA (Vol. 97, pp. 6555\u20136565). PMLR. http:\/\/proceedings.mlr.press\/v97\/wang19f.html"},{"key":"CIT0046","author":"Wang G.","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"CIT0047","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2021.102102"},{"key":"CIT0048","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.496"},{"key":"CIT0049","unstructured":"Williams, J. (1993). Narrow-band analyzer [Unpublished doctoral dissertation]. Dept. Elect. Eng., Harvard Univ."},{"key":"CIT0050","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2020.1806206"},{"key":"CIT0051","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3069562"},{"key":"CIT0052","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N. & Beyer, L. (2021). Scaling vision transformers. CoRR abs\/2106.04560. https:\/\/arxiv.org\/abs\/2106.04560"},{"key":"CIT0053","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"CIT0054","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.37"},{"issue":"1","key":"CIT0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107040","volume":"98","author":"Zhou L.","year":"2020","journal-title":"Pattern Recognition"},{"key":"CIT0056","unstructured":"Zhu, M., Han, K., Tang, Y. & Wang, Y. (2021). Visual transformer pruning. CoRR abs\/2104.08500. https:\/\/arxiv.org\/abs\/2104.08500"}],"container-title":["Connection Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/09540091.2021.2024510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T15:34:26Z","timestamp":1681745666000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/09540091.2021.2024510"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,17]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12,31]]}},"alternative-id":["10.1080\/09540091.2021.2024510"],"URL":"https:\/\/doi.org\/10.1080\/09540091.2021.2024510","relation":{},"ISSN":["0954-0091","1360-0494"],"issn-type":[{"value":"0954-0091","type":"print"},{"value":"1360-0494","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,17]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ccos20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ccos20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2021-08-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}