{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:38:31Z","timestamp":1783636711834,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543663","type":"print"},{"value":"9789819543670","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-4367-0_43","type":"book-chapter","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:38:31Z","timestamp":1763728711000},"page":"640-654","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["HEMQ: Towards More Accurate Post-training Mixed-Precision Quantization of\u00a0Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0447-5241","authenticated-orcid":false,"given":"Yong","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"43_CR1","unstructured":"Banner, R., Nahshan, Y., Soudry, D.: Post training 4-bit quantization of convolutional networks for rapid-deployment. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"1","key":"43_CR2","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1109\/MSP.2017.2765695","volume":"35","author":"Y Cheng","year":"2018","unstructured":"Cheng, Y., Wang, D., Zhou, P., Zhang, T.: Model compression and acceleration for deep neural networks: the principles, progress, and challenges. IEEE Signal Process. Mag. 35(1), 126\u2013136 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"43_CR3","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.J., Srinivasan, V., Gopalakrishnan, K.: Pact: parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085 (2018)"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Dong, Z., Yao, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: Hawq: hessian aware quantization of neural networks with mixed-precision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 293\u2013302 (2019)","DOI":"10.1109\/ICCV.2019.00038"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Liu, J., Niu, L., Yuan, Z., Yang, D., Wang, X., Liu, W.: PD-quant: post-training quantization based on prediction difference metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24427\u201324437 (2023)","DOI":"10.1109\/CVPR52729.2023.02340"},{"issue":"2","key":"43_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","volume":"56","author":"B Min","year":"2023","unstructured":"Min, B., et al.: Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surv. 56(2), 1\u201340 (2023)","journal-title":"ACM Comput. Surv."},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Mirjalili, S., Mirjalili, S.: Genetic algorithm. In: Evolutionary Algorithms and Neural Networks: Theory and Applications, pp. 43\u201355 (2019)","DOI":"10.1007\/978-3-319-93025-1_4"},{"key":"43_CR8","unstructured":"Nagel, M., Amjad, R.A., Van\u00a0Baalen, M., Louizos, C., Blankevoort, T.: Up or down? Adaptive rounding for post-training quantization. In: International Conference on Machine Learning, pp. 7197\u20137206. PMLR (2020)"},{"issue":"2","key":"43_CR9","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/TEVC.2008.927706","volume":"13","author":"AK Qin","year":"2008","unstructured":"Qin, A.K., Huang, V.L., Suganthan, P.N.: Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans. Evol. Comput. 13(2), 398\u2013417 (2008)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8612\u20138620 (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"43_CR11","unstructured":"Wei, X., Gong, R., Li, Y., Liu, X., Yu, F.: Qdrop: randomly dropping quantization for extremely low-bit post-training quantization. arXiv preprint arXiv:2203.05740 (2022)"},{"key":"43_CR12","unstructured":"Wu, B., Wang, Y., Zhang, P., Tian, Y., Vajda, P., Keutzer, K.: Mixed precision quantization of convnets via differentiable neural architecture search. arXiv preprint arXiv:1812.00090 (2018)"},{"key":"43_CR13","unstructured":"Yao, Z., et al.: Hawq-v3: dyadic neural network quantization. In: International Conference on Machine Learning, pp. 11875\u201311886. PMLR (2021)"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, C., Hu, X., Peng, S.: Evoq: mixed precision quantization of DNNs via sensitivity guided evolutionary search. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207413"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yang, J., Ye, D., Hua, G.: LQ-nets: learned quantization for highly accurate and compact deep neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 365\u2013382 (2018)","DOI":"10.1007\/978-3-030-01237-3_23"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4367-0_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:38:17Z","timestamp":1783107497000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4367-0_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"ISBN":["9789819543663","9789819543670"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4367-0_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"22 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"It is now necessary to declare any competing interests or to specifically state that the authors have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}