{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:51Z","timestamp":1763190831600,"version":"3.45.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228370","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Accelerated Dropout: A Bitmask Approach to Speed Up Model Training"],"prefix":"10.1109","author":[{"given":"Jincheng","family":"Xie","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Shi","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sicheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Ming","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Theory Lab, Central Research Institute, 2012 Labs,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Mathematical Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Improving neural networks by preventing co-adaptation of feature detectors","year":"2012","author":"Hinton","key":"ref1"},{"issue":"1","key":"ref2","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"article-title":"M6: A chinese multimodal pretrainer","year":"2021","author":"Lin","key":"ref3"},{"article-title":"Pangualpha: Large-scale autoregressive pretrained chinese language models with auto-parallel computation","year":"2021","author":"Zeng","key":"ref4"},{"article-title":"Pangu-{\\Sigma}: Towards trillion parameter language model with sparse heterogeneous computing","year":"2023","author":"Ren","key":"ref5"},{"key":"ref6","first-page":"881","article-title":"Rammer: Enabling holistic deep learning compiler optimizations with {rTasks}","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Ma"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"key":"ref8","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","year":"2023","author":"Dao","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2193"},{"article-title":"Sageattention: Accurate 8-bit attention for plug-and-play inference acceleration","year":"2024","author":"Zhang","key":"ref11"},{"article-title":"Sageattention2 technical report: Accurate 4 bit attention for plug-and-play inference acceleration","year":"2024","author":"Zhang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref15"},{"article-title":"Llama 2: Open foundation and finetuned chat models","year":"2023","author":"Touvron","key":"ref16"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref17"},{"issue":"8","key":"ref18","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref23"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"article-title":"Mixtral of experts","year":"2024","author":"Jiang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1117201.1117205"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CANDAR.2015.11"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"article-title":"Xnor-net++: Improved binary neural networks","year":"2019","author":"Bulat","key":"ref30"},{"article-title":"An empirical study of binary neural networks\u2019 optimisation","volume-title":"International conference on learning representations","author":"Alizadeh","key":"ref31"},{"article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","year":"2015","author":"Han","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_41"},{"article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","year":"2016","author":"Zhou","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/14786440009463897"},{"article-title":"Muse: Parallel multi-scale attention for sequence to sequence learning","year":"2019","author":"Zhao","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.71"},{"article-title":"Adaptive input representations for neural language modeling","volume-title":"International Conference on Learning Representations","author":"Baevski","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.217"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228370.pdf?arnumber=11228370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:12:10Z","timestamp":1763190730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228370","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}