{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:30:43Z","timestamp":1760711443318,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIST","award":["60NANB23D152"],"award-info":[{"award-number":["60NANB23D152"]}]},{"name":"NSF","award":["CNS 2335687, ATD 2123761, CNS 1822118"],"award-info":[{"award-number":["CNS 2335687, ATD 2123761, CNS 1822118"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679603","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"674-684","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5000-1242","authenticated-orcid":false,"given":"Matt","family":"Gorbett","sequence":"first","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2721-0628","authenticated-orcid":false,"given":"Hossein","family":"Shirazi","sequence":"additional","affiliation":[{"name":"San Diego State University, San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0714-7676","authenticated-orcid":false,"given":"Indrakshi","family":"Ray","sequence":"additional","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Learning and generalization in overparameterized neural networks, going beyond two layers. Advances in neural information processing systems","author":"Allen-Zhu Zeyuan","year":"2019","unstructured":"Zeyuan Allen-Zhu, Yuanzhi Li, and Yingyu Liang. 2019. Learning and generalization in overparameterized neural networks, going beyond two layers. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_4_1","volume-title":"A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282","author":"Cheng Yu","year":"2017","unstructured":"Yu Cheng, Duo Wang, Pan Zhou, and Tao Zhang. 2017. A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017)."},{"key":"e_1_3_2_1_5_1","unstructured":"Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser et al. 2020. Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"e_1_3_2_1_7_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to 1 or-1. arXiv preprint arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to 1 or-1. arXiv preprint arXiv:1602.02830 (2016)."},{"key":"e_1_3_2_1_8_1","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16344--16359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Diffenderfer James","year":"2020","unstructured":"James Diffenderfer and Bhavya Kailkhura. 2020. Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635","author":"Frankle Jonathan","year":"2018","unstructured":"Jonathan Frankle and Michael Carbin. 2018. The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635 (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00009"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-10684-2_9"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3532105.3535038"},{"key":"e_1_3_2_1_16_1","volume-title":"Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment. In 2023 IEEE International Conference on Big Data (BigData). IEEE, 5233--5242","author":"Gorbett Matt","year":"2023","unstructured":"Matt Gorbett, Hossein Shirazi, and Indrakshi Ray. 2023. Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment. In 2023 IEEE International Conference on Big Data (BigData). IEEE, 5233--5242."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599508"},{"key":"e_1_3_2_1_18_1","volume-title":"The intrinsic dimensionality of network datasets and its applications 1. Journal of Computer Security Preprint","author":"Gorbett Matt","year":"2023","unstructured":"Matt Gorbett, Caspian Siebert, Hossein Shirazi, and Indrakshi Ray. 2023. The intrinsic dimensionality of network datasets and its applications 1. Journal of Computer Security Preprint (2023), 1--26."},{"key":"e_1_3_2_1_19_1","volume-title":"Randomly initialized subnetworks with iterative weight recycling. arXiv preprint arXiv:2303.15953","author":"Gorbett Matt","year":"2023","unstructured":"Matt Gorbett and Darrell Whitley. 2023. Randomly initialized subnetworks with iterative weight recycling. arXiv preprint arXiv:2303.15953 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_2_1_22_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_23_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-021-01605-0"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242044"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062189"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17002"},{"key":"e_1_3_2_1_28_1","volume-title":"Low-Rank Factorization of Weight Matrices in Neural Networks. arXiv preprint arXiv:1511.06441","author":"Lebedev Vadim","year":"2014","unstructured":"Vadim Lebedev, Yaroslav Ganin, Maksim Rakhuba, Ivan Oseledets, and Victor Lempitsky. 2014. Low-Rank Factorization of Weight Matrices in Neural Networks. arXiv preprint arXiv:1511.06441 (2014)."},{"key":"e_1_3_2_1_29_1","volume-title":"Byeongwook Kim, Yongkweon Jeon, Baeseong Park, and Jeongin Yun.","author":"Lee Dongsoo","year":"2020","unstructured":"Dongsoo Lee, Se Jung Kwon, Byeongwook Kim, Yongkweon Jeon, Baeseong Park, and Jeongin Yun. 2020. FleXOR: Trainable Fractional Quantization. arxiv: 2009.04126 [cs.LG]"},{"key":"e_1_3_2_1_30_1","volume-title":"Learning overparameterized neural networks via stochastic gradient descent on structured data. Advances in neural information processing systems","author":"Li Yuanzhi","year":"2018","unstructured":"Yuanzhi Li and Yingyu Liang. 2018. Learning overparameterized neural networks via stochastic gradient descent on structured data. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on machine learning. PMLR, 2849--2858","author":"Lin Darryl","year":"2016","unstructured":"Darryl Lin, Sachin Talathi, and Sreekanth Annapureddy. 2016. Fixed point quantization of deep convolutional networks. In International conference on machine learning. PMLR, 2849--2858."},{"key":"e_1_3_2_1_32_1","volume-title":"Mcunetv2: Memory-efficient patch-based inference for tiny deep learning. arXiv preprint arXiv:2110.15352","author":"Lin Ji","year":"2021","unstructured":"Ji Lin, Wei-Ming Chen, Han Cai, Chuang Gan, and Song Han. 2021. Mcunetv2: Memory-efficient patch-based inference for tiny deep learning. arXiv preprint arXiv:2110.15352 (2021)."},{"key":"e_1_3_2_1_33_1","first-page":"11711","article-title":"Mcunet: Tiny deep learning on iot devices","volume":"33","author":"Lin Ji","year":"2020","unstructured":"Ji Lin, Wei-Ming Chen, Yujun Lin, Chuang Gan, Song Han, et al. 2020. Mcunet: Tiny deep learning on iot devices. Advances in Neural Information Processing Systems, Vol. 33 (2020), 11711--11722.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","first-page":"22941","article-title":"On-device training under 256kb memory","volume":"35","author":"Lin Ji","year":"2022","unstructured":"Ji Lin, Ligeng Zhu, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, and Song Han. 2022. On-device training under 256kb memory. Advances in Neural Information Processing Systems, Vol. 35 (2022), 22941--22954.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings, Part XIV 16","author":"Liu Zechun","year":"2020","unstructured":"Zechun Liu, Zhiqiang Shen, Marios Savvides, and Kwang-Ting Cheng. 2020. Reactnet: Towards precise binary neural network with generalized activation functions. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIV 16. Springer, 143--159."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_2_1_38_1","volume-title":"Training binary neural networks with real-to-binary convolutions. arXiv preprint arXiv:2003.11535","author":"Martinez Brais","year":"2020","unstructured":"Brais Martinez, Jing Yang, Adrian Bulat, and Georgios Tzimiropoulos. 2020. Training binary neural networks with real-to-binary convolutions. arXiv preprint arXiv:2003.11535 (2020)."},{"key":"e_1_3_2_1_39_1","unstructured":"Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR 1273--1282."},{"key":"e_1_3_2_1_40_1","volume-title":"Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort.","author":"Nagel Markus","year":"2021","unstructured":"Markus Nagel, Marios Fournarakis, Rana Ali Amjad, Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort. 2021. A white paper on neural network quantization. arXiv preprint arXiv:2106.08295 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 652--660","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 652--660."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Qin Haotong","year":"2023","unstructured":"Haotong Qin, Mingyuan Zhang, Yifu Ding, Aoyu Li, Zhongang Cai, Ziwei Liu, Fisher Yu, and Xianglong Liu. 2023. BiBench: Benchmarking and Analyzing Network Binarization. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML'23). JMLR.org, Article 1177, 38 pages."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01191"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_2_1_48_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2014","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)."},{"key":"e_1_3_2_1_49_1","first-page":"326","article-title":"Memory-driven mixed low precision quantization for enabling deep network inference on microcontrollers","volume":"2","author":"Rusci Manuele","year":"2020","unstructured":"Manuele Rusci, Alessandro Capotondi, and Luca Benini. 2020. Memory-driven mixed low precision quantization for enabling deep network inference on microcontrollers. Proceedings of Machine Learning and Systems, Vol. 2 (2020), 326--335.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_51_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_35"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_54_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al. 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems, Vol. 34 (2021), 24261--24272."},{"key":"e_1_3_2_1_55_1","volume-title":"Patches are all you need? arXiv preprint arXiv:2201.09792","author":"Trockman Asher","year":"2022","unstructured":"Asher Trockman and J Zico Kolter. 2022. Patches are all you need? arXiv preprint arXiv:2201.09792 (2022)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00560"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02335"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00531"},{"key":"e_1_3_2_1_59_1","first-page":"25553","article-title":"Learning frequency domain approximation for binary neural networks","volume":"34","author":"Xu Yixing","year":"2021","unstructured":"Yixing Xu, Kai Han, Chang Xu, Yehui Tang, Chunjing Xu, and Yunhe Wang. 2021. Learning frequency domain approximation for binary neural networks. Advances in Neural Information Processing Systems, Vol. 34 (2021), 25553--25565.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00515"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467401"},{"key":"e_1_3_2_1_62_1","volume-title":"Incremental network quantization: Towards lossless cnns with low-precision weights. arXiv preprint arXiv:1702.03044","author":"Zhou Aojun","year":"2017","unstructured":"Aojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, and Yurong Chen. 2017. Incremental network quantization: Towards lossless cnns with low-precision weights. arXiv preprint arXiv:1702.03044 (2017)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Boise ID USA","acronym":"CIKM '24"},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679603","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:23Z","timestamp":1750294703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":64,"alternative-id":["10.1145\/3627673.3679603","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679603","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}