{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:14:22Z","timestamp":1774419262464,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890336","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Class-wise Adaptive Logits Distillation with Meta-Learning"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Huang","sequence":"first","affiliation":[{"name":"Southwest University,College of Computer and Information Science College of Software,Chongqing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Chen","sequence":"additional","affiliation":[{"name":"Southwest University,College of Computer and Information Science College of Software,Chongqing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chongqing University,School of Big Data & Software Engineering,Chongqing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref2","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref3","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref4","article-title":"Knowledge distillation as semiparametric inference","author":"Dao","year":"2021","journal-title":"ICLR"},{"key":"ref5","article-title":"Fitnets: Hints for thin deep nets","volume-title":"ICLR","author":"Romero","year":"2015"},{"key":"ref6","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"ICLR","author":"Zagoruyko","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01576"},{"key":"ref10","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2015","journal-title":"ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_20"},{"key":"ref12","article-title":"Explicit connection distillation","author":"Li","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891976"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892575"},{"key":"ref15","article-title":"Catch-up distillation: You only need to train once for accelerating sampling","author":"Shao","year":"2023"},{"key":"ref16","article-title":"Shadow knowledge distillation: Bridging offline and online knowledge transfer","author":"Li","year":"2022","journal-title":"NeuIPS"},{"key":"ref17","article-title":"Norm: Knowledge distillation via n-to-one representation matching","author":"Xiaolong","year":"2022"},{"key":"ref18","article-title":"Knowledge distillation from a stronger teacher","volume-title":"NeurIPS","author":"Huang","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01597"},{"key":"ref21","article-title":"Kd-zero: Evolving knowledge distiller for any teacher-student pairs","author":"Li","year":"2024","journal-title":"NeuIPS"},{"key":"ref22","article-title":"Detkds: Knowledge distillation search for object detectors","author":"Li","year":"2024","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_4"},{"key":"ref24","article-title":"Fidelity-weighted learning","author":"Dehghani","year":"2018","journal-title":"ICLR"},{"key":"ref25","article-title":"Learning to teach","author":"Fan","year":"2018","journal-title":"ICLR"},{"key":"ref26","article-title":"Learning to teach with dynamic loss functions","author":"Wu","year":"2018","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels","author":"Jiang","year":"2018","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108025"},{"key":"ref29","article-title":"Prior-guided one-shot neural architecture search","author":"Dong","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29327"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29511"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28606"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33793"},{"key":"ref34","article-title":"Gp-nas-ensemble: a model for the nas performance prediction","author":"Chen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_3"},{"key":"ref37","first-page":"48","volume-title":"Approximation with artificial neural networks","volume":"24","author":"Cs\u00e1ji","year":"2001"},{"key":"ref38","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","author":"Franceschi","year":"2018","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref40","article-title":"Contrastive representation distillation","volume-title":"ICLR","author":"Tian","year":"2020"},{"key":"ref41","article-title":"Knowledge distillation via softmax regression representation learning","volume-title":"ICLR","author":"Yang","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref43","article-title":"One-for-all: Bridge the gap between heterogeneous architectures in knowledge distillation","volume-title":"NeurIPS","author":"Hao","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref45","article-title":"Training data-efficient image transformers amp; distillation through attention","author":"Touvron","year":"2021","journal-title":"ICML"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","article-title":"Als: Adaptive layer sparsity for large language models via activation correlation assessment","author":"Li","year":"2024","journal-title":"NeuIPS"},{"key":"ref48","article-title":"Discovering sparsity allocation for layer-wise pruning of large language models","author":"Li","year":"2024","journal-title":"NeuIPS"},{"key":"ref49","article-title":"Pruner-zero: Evolving symbolic pruning metric from scratch for large language models","author":"Dong","year":"2024","journal-title":"ICML"},{"key":"ref50","article-title":"Nora: Nested low-rank adaptation for efficient fine-tuning large models","author":"Lin","year":"2024"},{"key":"ref51","article-title":"Stbllm: Breaking the 1-bit barrier with structured binary llms","author":"Dong","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20108"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890336.pdf?arnumber=10890336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:56Z","timestamp":1774416116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890336","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}