{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:17:59Z","timestamp":1774419479556,"version":"3.50.1"},"reference-count":56,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888554","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":3,"title":["Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models"],"prefix":"10.1109","author":[{"given":"Yize","family":"Li","sequence":"first","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,USA"}]},{"given":"Yihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Michigan State University,Department of Computer Science and Engineering,East Lansing,USA"}]},{"given":"Sijia","family":"Liu","sequence":"additional","affiliation":[{"name":"Michigan State University,Department of Computer Science and Engineering,East Lansing,USA"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref3","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref6","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626172"},{"key":"ref8","article-title":"Parameter-efficient fine-tuning for pre-trained vision models: A survey","author":"Xin","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref10","article-title":"Ecnet: Effective controllable text-to-image diffusion models","author":"Li","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_14"},{"key":"ref12","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref14","article-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","author":"Liu","year":"2024","journal-title":"ICLR"},{"key":"ref16","article-title":"Patch diffusion: Faster and more data-efficient training of diffusion models","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"2024","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref18","article-title":"Fast diffusion model","author":"Wu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"ref20","article-title":"Instance selection for gans","author":"DeVries","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref22","article-title":"Reverse engineering of imperceptible adversarial image perturbations","author":"Gong","year":"2022","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"ref27","article-title":"Moderate coreset: A universal method of data selection for real-world data-efficient deep learning","author":"Xia","year":"2023","journal-title":"ICLR"},{"key":"ref28","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"Sagawa","year":"2020","journal-title":"ICLR"},{"key":"ref29","article-title":"Doremi: Optimizing data mixtures speeds up language model pretraining","author":"Xie","year":"2023","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref32","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref37","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref40","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref41","article-title":"Structural pruning for diffusion models","author":"Fang","year":"2024","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3389\/fhpcp.2024.1301384"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"ref46","article-title":"Coresets via bilevel optimization for continual learning and streaming","author":"Borsos","year":"2020","journal-title":"NeurIPS"},{"key":"ref47","article-title":"Less is more: Data pruning for faster adversarial training","volume-title":"SafeAI Workshop on AAAI","author":"Li"},{"key":"ref48","article-title":"Deep learning on a data diet: Finding important examples early in training","author":"Paul","year":"2021","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Dataset pruning: Reducing training data by examining generalization influence","author":"Yang","year":"2023","journal-title":"ICLR"},{"key":"ref50","article-title":"Grad-match: Gradient matching based data subset selection for efficient deep model training","author":"Killamsetty","year":"2021","journal-title":"ICML"},{"key":"ref51","article-title":"Prioritized training on points that are learnable, worth learning, and not yet learnt","author":"Mindermann","year":"2022","journal-title":"ICML"},{"key":"ref52","article-title":"Infobatch: Lossless training speed up by unbiased dynamic data pruning","author":"Qin","year":"2024","journal-title":"ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3423382"},{"key":"ref55","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"}],"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\/10888554.pdf?arnumber=10888554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:02Z","timestamp":1774416182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888554","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}