{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T03:20:50Z","timestamp":1779247250590,"version":"3.51.4"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong and Macau Youth Supporting Fund from the Guangzhou Association of Science and Technology"},{"name":"Research Committee of The Hong Kong Polytechnic University","award":["RL3C"],"award-info":[{"award-number":["RL3C"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3588894","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T17:42:17Z","timestamp":1752601337000},"page":"9702-9717","source":"Crossref","is-referenced-by-count":2,"title":["One Neuron Saved is One Neuron Earned: On Parametric Efficiency of Quadratic Networks"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3691-5141","authenticated-orcid":false,"given":"Feng-Lei","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Data Science, Frontier of Artificial Network (FAN) Lab, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4880-6762","authenticated-orcid":false,"given":"Hang-Cheng","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9128-5181","authenticated-orcid":false,"given":"Zhongming","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Management Science and Engineering, Nanjing University of Information Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5061-3575","authenticated-orcid":false,"given":"Lecheng","family":"Ruan","sequence":"additional","affiliation":[{"name":"College of Engineering, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0688-202X","authenticated-orcid":false,"given":"Tieyong","family":"Zeng","sequence":"additional","affiliation":[{"name":"Institute for Advanced Study, Beijing Normal-Hong Kong Baptist University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2423-8972","authenticated-orcid":false,"given":"Yiming","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1880-2621","authenticated-orcid":false,"given":"Jing-Xiao","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02478259"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-46466-9_18"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37180-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s44258-024-00042-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03941-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.2920"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331380"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2963248"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3259031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2024.111750"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.01.007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.07.002"},{"key":"ref15","first-page":"8174","article-title":"Efficient approximation of deep ReLU networks for functions on low dimensional manifolds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF01171759"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1971.4308320"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155142"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.548936"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3124328"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.510"},{"key":"ref23","first-page":"1","article-title":"Mixed precision training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Micikevicius"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04316-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413207"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976700.76"},{"key":"ref27","first-page":"503","article-title":"QuadraLib: A performant quadratic neural network library for architecture optimization and design exploration","volume-title":"Proc. Mach. Learn. Syst.","volume":"4","author":"Xu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207535"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3231971"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2016.00023"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1101\/2021.10.25.465651","article-title":"Going beyond the point neuron: Active dendrites and sparse representations for continual learning","author":"Grewal","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1677-2"},{"key":"ref34","first-page":"23426","article-title":"Differentiable spike: Rethinking gradient-descent for training spiking neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref37","first-page":"1","article-title":"Multiplicative interactions and where to find them","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jayakumar"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"ref39","first-page":"1","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01035"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00610"},{"key":"ref45","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref46","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024"},{"key":"ref47","article-title":"Gated slot attention for efficient linear-time sequence modeling","author":"Zhang","year":"2024"},{"key":"ref48","article-title":"Retentive network: A successor to transformer for large language models","author":"Sun","year":"2023"},{"key":"ref49","first-page":"10310","article-title":"On the expressive power of deep polynomial neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kileel"},{"key":"ref50","first-page":"3517","article-title":"Sound and complete verification of polynomial networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Abad Rocamora"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12422"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-022-00118-z"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_40"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01547"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106611"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1190\/geo2024-0019.1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s40430-025-05457-5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2020-0149"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1137\/20M134695X"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-021-09549-y"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/18.256500"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023541"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref65","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref66","first-page":"1","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00169"},{"key":"ref68","first-page":"5105","article-title":"PointNet: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref69","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/MIA.2007.909802"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2021.110242"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.pnucene.2022.104344"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3390\/s20185112"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2955540"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3390\/s17020425"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/naecon.2018.8556686"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref83","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref84","article-title":"A foundation model for cell segmentation","author":"Israel","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01182-1"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1038\/s41576-022-00515-3"},{"key":"ref87","article-title":"Cell segmentation by combining marker-controlled watershed and deep learning","author":"Lux","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.01110"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE48569.2019.8964956"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2795531"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref93","first-page":"6","article-title":"Annotated image datasets of rosette plants","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Scharr"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref96","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref97","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266435"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3105820"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref103","first-page":"16945","article-title":"Compressing large language models by joint sparsification and quantization","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01509"},{"key":"ref105","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref106","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11080117.pdf?arnumber=11080117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:52Z","timestamp":1759772212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11080117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":106,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3588894","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}