{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:56:53Z","timestamp":1768942613046,"version":"3.49.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006407","name":"Henan Province Natural Science Foundation","doi-asserted-by":"publisher","award":["252300420990"],"award-info":[{"award-number":["252300420990"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["252102211040"],"award-info":[{"award-number":["252102211040"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276153"],"award-info":[{"award-number":["62276153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.neunet.2025.108229","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T06:47:27Z","timestamp":1760683647000},"page":"108229","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Gradient-aware knowledge distillation: Tackling gradient insensitivity through teacher guided gradient scaling"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-4325","authenticated-orcid":false,"given":"Nianwen","family":"Si","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3841-1959","authenticated-orcid":false,"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heyu","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108229_bib0001","series-title":"Proceedings of COMPSTAT\u20192010","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"Bottou","year":"2010"},{"key":"10.1016\/j.neunet.2025.108229_bib0002","series-title":"2022\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"11923","article-title":"Knowledge distillation with the reused teacher classifier","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2025.108229_bib0003","series-title":"2021\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"5006","article-title":"Distilling knowledge via knowledge review","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2025.108229_bib0004","doi-asserted-by":"crossref","first-page":"7901","DOI":"10.1109\/TMM.2024.3372833","article-title":"Reciprocal teacher-student learning via forward and feedback knowledge distillation","volume":"26","author":"Gou","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108229_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107404","article-title":"Intra-class progressive and adaptive self-distillation","volume":"188","author":"Gou","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108229_bib0006","series-title":"2023\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"11868","article-title":"Class attention transfer based knowledge distillation","author":"Guo","year":"2023"},{"key":"10.1016\/j.neunet.2025.108229_bib0007","series-title":"2016\u202fIEEE Conference on computer vision and pattern recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2025.108229_bib0008","series-title":"2019\u202fIEEE\/CVF International conference on computer vision (ICCV)","first-page":"1921","article-title":"A comprehensive overhaul of feature distillation","author":"Heo","year":"2019"},{"key":"10.1016\/j.neunet.2025.108229_bib0009","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. https:\/\/arxiv.org\/abs\/1503.02531."},{"key":"10.1016\/j.neunet.2025.108229_bib0010","series-title":"International conference on representation learning","article-title":"Single teacher, multiple perspectives: Teacher knowledge augmentation for enhanced knowledge distillation","volume":"2025","author":"Hossain","year":"2025"},{"key":"10.1016\/j.neunet.2025.108229_bib0011","series-title":"2023\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"24276","article-title":"Multi-level logit distillation","author":"Jin","year":"2023"},{"key":"10.1016\/j.neunet.2025.108229_bib0012","unstructured":"Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images: Technical report, Neural Networks."},{"key":"10.1016\/j.neunet.2025.108229_bib0013","series-title":"Findings of the association for computational linguistics: ACL 2023 Toronto, Canada","first-page":"3123","article-title":"CKDST: Comprehensively and effectively distill knowledge from machine translation to end-to-end speech translation","author":"Lei","year":"2023"},{"key":"10.1016\/j.neunet.2025.108229_bib0014","series-title":"Curriculum temperature for knowledge distillation AAAI\u201923\/IAAI\u201923\/EAAI\u201923","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2025.108229_bib0015","series-title":"2017\u202fIEEE Conference on computer vision and pattern recognition (CVPR)","first-page":"936","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2025.108229_bib0016","series-title":"Computer vision \u2013 ECCV 2014","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2025.108229_bib0017","unstructured":"Liu, D., Kan, M., Shan, S., & Chen, X. (2023a). Function-consistent feature distillation. arXiv: 2304.11832."},{"key":"10.1016\/j.neunet.2025.108229_bib0018","unstructured":"Liu, X., Li, L., Li, C., & Yao, A. (2023b). Norm: Knowledge distillation via n-to-one representation matching. https:\/\/api.semanticscholar.org\/CorpusID:258841675."},{"key":"10.1016\/j.neunet.2025.108229_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.107940","article-title":"Latent domain knowledge distillation for nighttime semantic segmentation","volume":"132","author":"Liu","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2025.108229_bib0020","series-title":"Computer vision \u2013 ECCV 2018","first-page":"122","article-title":"ShuffleNet v2: Practical guidelines for efficient CNN architecture design","author":"Ma","year":"2018"},{"key":"10.1016\/j.neunet.2025.108229_bib0021","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5191","article-title":"Improved knowledge distillation via teacher assistant","volume":"34","author":"Mirzadeh","year":"2020"},{"key":"10.1016\/j.neunet.2025.108229_bib0022","series-title":"2019\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"3962","article-title":"Relational knowledge distillation","author":"Park","year":"2019"},{"issue":"6","key":"10.1016\/j.neunet.2025.108229_bib0023","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108229_bib0024","unstructured":"Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2015). Fitnets: Hints for thin deep nets. https:\/\/arxiv.org\/abs\/1412.6550."},{"key":"10.1016\/j.neunet.2025.108229_bib0025","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., & Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. arXiv: 1409.0575.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"10.1016\/j.neunet.2025.108229_bib0026","series-title":"2018\u202fIEEE\/CVF Conference on computer vision and pattern recognition","first-page":"4510","article-title":"MobileNetv2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"10.1016\/j.neunet.2025.108229_bib0027","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556."},{"key":"10.1016\/j.neunet.2025.108229_bib0028","series-title":"2024\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"15731","article-title":"Logit standardization in knowledge distillation","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2025.108229_bib0029","series-title":"2024\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"15731","article-title":"Logit standardization in knowledge distillation","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2025.108229_bib0030","unstructured":"Sun, W., Chen, D., Lyu, S., Chen, G., Chen, C., & Wang, C. (2024c). Knowledge distillation with refined logits. arXiv: 2408.07703https:\/\/api.semanticscholar.org\/CorpusID:271865571."},{"key":"10.1016\/j.neunet.2025.108229_bib0031","unstructured":"Tian, Y., Krishnan, D., & Isola, P. (2019). Contrastive representation distillation. arXiv: 1910.10699. https:\/\/api.semanticscholar.org\/CorpusID:204838340."},{"issue":"86","key":"10.1016\/j.neunet.2025.108229_bib0032","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2025.108229_bib0033","series-title":"2019\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"4928","article-title":"Distilling object detectors with fine-grained feature imitation","author":"Wang","year":"2019"},{"key":"10.1016\/j.neunet.2025.108229_bib0034","series-title":"2024\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"15975","article-title":"Scale decoupled distillation","author":"Wei","year":"2024"},{"key":"10.1016\/j.neunet.2025.108229_bib0035","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., & Girshick, R. (2019). Detectron2. https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"10.1016\/j.neunet.2025.108229_bib0036","unstructured":"Xu, L., Liu, K., Liu, J., Wang, L., Xu, L., & Cheng, J. (2025). Local dense logit relations for enhanced knowledge distillation. arXiv: 2507.15911."},{"key":"10.1016\/j.neunet.2025.108229_bib0037","unstructured":"Zagoruyko, S., & Komodakis, N. (2017). Wide residual networks. arXiv: 1605.07146."},{"key":"10.1016\/j.neunet.2025.108229_bib0038","series-title":"ICASSP 2023 - 2023 IEEE international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"Decoupled non-parametric knowledge distillation for end-to-end speech translation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2025.108229_bib0039","series-title":"2023\u202fIEEE\/CVF International conference on computer vision (ICCV)","first-page":"6166","article-title":"Dot: A distillation-oriented trainer","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2025.108229_bib0040","series-title":"2022\u202fIEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"11943","article-title":"Decoupled knowledge distillation","author":"Zhao","year":"2022"},{"key":"10.1016\/j.neunet.2025.108229_bib0041","series-title":"ICASSP 2023 - 2023 IEEE international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"Hierarchical network with decoupled knowledge distillation for speech emotion recognition","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2025.108229_bib0042","unstructured":"Zheng, K., & Yang, E.-H. (2024). Knowledge distillation based on transformed teacher matching. arXiv: 2402.11148. https:\/\/api.semanticscholar.org\/CorpusID:267751335."},{"key":"10.1016\/j.neunet.2025.108229_bib0043","unstructured":"Zhou, Z., Shen, Y., Shao, S., Chen, H., Gong, L., & Lin, S. (2024). Rethinking centered kernel alignment in knowledge distillation. https:\/\/api.semanticscholar.org\/CorpusID:267069331."},{"issue":"7","key":"10.1016\/j.neunet.2025.108229_bib0044","doi-asserted-by":"crossref","first-page":"5255","DOI":"10.1109\/TCSVT.2023.3342879","article-title":"Intermediate domain-based meta learning framework for adaptive object detection","volume":"34","author":"Zhu","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011104?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011104?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T07:29:29Z","timestamp":1768894169000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025011104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":44,"alternative-id":["S0893608025011104"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108229","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Gradient-aware knowledge distillation: Tackling gradient insensitivity through teacher guided gradient scaling","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108229","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108229"}}