{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T16:13:43Z","timestamp":1785514423002,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":132,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642109","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:37:41Z","timestamp":1715416661000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-844X","authenticated-orcid":false,"given":"Fred","family":"Hohman","sequence":"first","affiliation":[{"name":"Apple, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1771-0565","authenticated-orcid":false,"given":"Mary Beth","family":"Kery","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8666-7241","authenticated-orcid":false,"given":"Donghao","family":"Ren","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3110-1053","authenticated-orcid":false,"given":"Dominik","family":"Moritz","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_2_1_1","volume-title":"What is the team data science process?Microsoft","year":"2018","unstructured":"2018. What is the team data science process?Microsoft (2018). https:\/\/learn.microsoft.com\/en-us\/azure\/architecture\/data-science-process\/overview"},{"key":"e_1_3_3_2_2_1","volume-title":"Design for AI. IBM","year":"2019","unstructured":"2019. Design for AI. IBM (2019). https:\/\/www.ibm.com\/design\/ai\/"},{"key":"e_1_3_3_2_3_1","volume-title":"Human interface guidelines: Machine learning. Apple Human Interface Guidelines","year":"2019","unstructured":"2019. Human interface guidelines: Machine learning. Apple Human Interface Guidelines (2019). https:\/\/developer.apple.com\/design\/human-interface-guidelines\/technologies\/machine-learning\/introduction"},{"key":"e_1_3_3_2_4_1","volume-title":"https:\/\/pair.withgoogle.com\/guidebook\/","author":"Google People","year":"2019","unstructured":"2019. People + AI guidebook. Google (2019). https:\/\/pair.withgoogle.com\/guidebook\/"},{"key":"e_1_3_3_2_5_1","volume-title":"Machine learning workflow. Google","year":"2023","unstructured":"2023. Machine learning workflow. Google (2023). https:\/\/cloud.google.com\/ai-platform\/docs\/ml-solutions-overview"},{"key":"e_1_3_3_2_6_1","volume-title":"Llm in a flash: Efficient large language model inference with limited memory. arXiv preprint arXiv:2312.11514","author":"Alizadeh Keivan","year":"2023","unstructured":"Keivan Alizadeh, Iman Mirzadeh, Dmitry Belenko, Karen Khatamifard, Minsik Cho, Carlo\u00a0C Del\u00a0Mundo, Mohammad Rastegari, and Mehrdad Farajtabar. 2023. Llm in a flash: Efficient large language model inference with limited memory. arXiv preprint arXiv:2312.11514 (2023)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse-seip.2019.00042"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_3_3_2_9_1","unstructured":"Apple. 2023. Optimizing models - Core ML Tools overview. https:\/\/coremltools.readme.io\/docs"},{"key":"e_1_3_3_2_10_1","unstructured":"Apple. 2023. Personalizing a model with on-device updates. https:\/\/developer.apple.com\/documentation\/coreml\/model_personalization\/personalizing_a_model_with_on-device_updates"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3375624"},{"key":"e_1_3_3_2_13_1","volume-title":"On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258","author":"Bommasani Rishi","year":"2021","unstructured":"Rishi Bommasani, Drew\u00a0A Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael\u00a0S Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)."},{"key":"e_1_3_3_2_14_1","volume-title":"Conducting in-depth interviews: A guide for designing and conducting in-depth interviews for evaluation input. Vol.\u00a02","author":"Boyce Carolyn","unstructured":"Carolyn Boyce and Palena Neale. 2006. Conducting in-depth interviews: A guide for designing and conducting in-depth interviews for evaluation input. Vol.\u00a02. Pathfinder International Watertown, MA."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287036"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2019.2921977"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2765695"},{"key":"e_1_3_3_2_18_1","volume-title":"International Conference on Learning Representations. https:\/\/arxiv.org\/abs\/2108","author":"Cho Minsik","year":"2022","unstructured":"Minsik Cho, Keivan\u00a0A. Vahid, Saurabh Adya, and Mohammad Rastegari. 2022. Differentiable k-means clustering layer for neural network compression. In International Conference on Learning Representations. https:\/\/arxiv.org\/abs\/2108.12659"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453531"},{"key":"e_1_3_3_2_21_1","volume-title":"\u201cadd diverse stakeholders and stir\u201d. arXiv","author":"Delgado Fernando","year":"2021","unstructured":"Fernando Delgado, Stephen Yang, Michael Madaio, and Qian Yang. 2021. Stakeholder participation in AI: Beyond \u201cadd diverse stakeholders and stir\u201d. arXiv (2021)."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2020.2976475"},{"key":"e_1_3_3_2_23_1","unstructured":"Google Developers. Accessed 2022. Why on-device machine learning?https:\/\/developers.google.com\/learn\/topics\/on-device-ml\/learn-more"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450494"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450494"},{"key":"e_1_3_3_2_26_1","volume-title":"Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models. arXiv preprint arXiv:2203.06904","author":"Ding Ning","year":"2022","unstructured":"Ning Ding, Yujia Qin, Guang Yang, Fuchao Wei, Zonghan Yang, Yusheng Su, Shengding Hu, Yulin Chen, Chi-Min Chan, Weize Chen, 2022. Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models. arXiv preprint arXiv:2203.06904 (2022)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_3_2_28_1","unstructured":"Farah Fahim Benjamin Hawks Christian Herwig James Hirschauer Sergo Jindariani Nhan Tran Luca\u00a0P Carloni Giuseppe Di\u00a0Guglielmo Philip Harris Jeffrey Krupa 2021. hls4ml: An open-source codesign workflow to empower scientific low-power machine learning devices. (2021). arXiv:2103.05579"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/240455.240464"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26505"},{"key":"e_1_3_3_2_31_1","volume-title":"The state of sparsity in deep neural networks. arXiv preprint arXiv:1902.09574","author":"Gale Trevor","year":"2019","unstructured":"Trevor Gale, Erich Elsen, and Sara Hooker. 2019. The state of sparsity in deep neural networks. arXiv preprint arXiv:1902.09574 (2019)."},{"key":"e_1_3_3_2_32_1","volume-title":"A survey of quantization methods for efficient neural network inference. arXiv","author":"Gholami Amir","year":"2021","unstructured":"Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael\u00a0W Mahoney, and Kurt Keutzer. 2021. A survey of quantization methods for efficient neural network inference. arXiv (2021). arXiv:2103.13630"},{"key":"e_1_3_3_2_33_1","volume-title":"Artificial intelligence. Our World in Data","author":"Giattino Charlie","year":"2022","unstructured":"Charlie Giattino, Edouard Mathieu, Veronika Samborska, Julia Broden, and Max Roser. 2022. Artificial intelligence. Our World in Data (2022). https:\/\/ourworldindata.org\/artificial-intelligence."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781849208574.n4"},{"key":"e_1_3_3_2_35_1","unstructured":"Google. 2019. QKeras. https:\/\/github.com\/google\/qkeras"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3424660"},{"key":"e_1_3_3_2_38_1","unstructured":"Song Han Huizi Mao and William\u00a0J Dally. 2016. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. (2016)."},{"key":"e_1_3_3_2_39_1","volume-title":"MLX: Efficient and flexible machine learning on Apple silicon. https:\/\/github.com\/ml-explore","author":"Hannun Awni","year":"2023","unstructured":"Awni Hannun, Jagrit Digani, Angelos Katharopoulos, and Ronan Collobert. 2023. MLX: Efficient and flexible machine learning on Apple silicon. https:\/\/github.com\/ml-explore"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/vlhcc.2016.7739680"},{"key":"e_1_3_3_2_41_1","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler Torsten","year":"2021","unstructured":"Torsten Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, and Alexandra Peste. 2021. Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks. Journal of Machine Learning Research 22, 241 (2021), 1\u2013124.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392878"},{"key":"e_1_3_3_2_44_1","volume-title":"What do compressed deep neural networks forget?arXiv preprint arXiv:1911.05248","author":"Hooker Sara","year":"2019","unstructured":"Sara Hooker, Aaron Courville, Gregory Clark, Yann Dauphin, and Andrea Frome. 2019. What do compressed deep neural networks forget?arXiv preprint arXiv:1911.05248 (2019)."},{"key":"e_1_3_3_2_45_1","volume-title":"Characterising bias in compressed models. arXiv","author":"Hooker Sara","year":"2020","unstructured":"Sara Hooker, Nyalleng Moorosi, Gregory Clark, Samy Bengio, and Emily Denton. 2020. Characterising bias in compressed models. arXiv (2020). arXiv:2010.03058"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462527"},{"key":"e_1_3_3_2_47_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv abs\/1704.04861","author":"Howard G","year":"2017","unstructured":"Andrew\u00a0G 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 abs\/1704.04861 (2017). arXiv:1704.04861"},{"key":"e_1_3_3_2_48_1","volume-title":"International Conference on Learning Representations","author":"Hu J","year":"2022","unstructured":"Edward\u00a0J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. International Conference on Learning Representations (2022)."},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2991416"},{"key":"e_1_3_3_2_50_1","unstructured":"Intel. 2020. Neural Compressor. https:\/\/github.com\/intel\/neural-compressor"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441303"},{"key":"e_1_3_3_2_52_1","first-page":"1","article-title":"Gan lab: Understanding complex deep generative models using interactive visual experimentation","volume":"25","author":"Kahng Minsuk","year":"2018","unstructured":"Minsuk Kahng, Nikhil Thorat, Duen Horng\u00a0Polo Chau, Fernanda\u00a0B Vi\u00e9gas, and Martin Wattenberg. 2018. Gan lab: Understanding complex deep generative models using interactive visual experimentation. IEEE Transactions on Visualization and Computer Graphics 25, 1 (2018), 1\u201311. https:\/\/poloclub.github.io\/ganlab\/","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-022-00150-6"},{"key":"e_1_3_3_2_54_1","volume-title":"Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492","author":"Kone\u010dn\u1ef3 Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u1ef3, H\u00a0Brendan McMahan, Felix\u00a0X Yu, Peter Richt\u00e1rik, Ananda\u00a0Theertha Suresh, and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492 (2016)."},{"key":"e_1_3_3_2_55_1","volume-title":"International Conference on Machine Learning. PMLR, 5544\u20135555","author":"Kusupati Aditya","year":"2020","unstructured":"Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham Kakade, and Ali Farhadi. 2020. Soft threshold weight reparameterization for learnable sparsity. In International Conference on Machine Learning. PMLR, 5544\u20135555."},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1177\/1077800406286235"},{"key":"e_1_3_3_2_57_1","volume-title":"Kevin Li, Haekyu Park, Haoyang Yang, and Duen\u00a0Horng Chau.","author":"Lee Seongmin","year":"2023","unstructured":"Seongmin Lee, Benjamin Hoover, Hendrik Strobelt, Zijie\u00a0J Wang, ShengYun Peng, Austin Wright, Kevin Li, Haekyu Park, Haoyang Yang, and Duen\u00a0Horng Chau. 2023. Diffusion explainer: Visual explanation for text-to-image stable diffusion. arXiv preprint arXiv:2305.03509 (2023)."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610903"},{"key":"e_1_3_3_2_59_1","volume-title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning. arXiv preprint arXiv:2303.15647","author":"Lialin Vladislav","year":"2023","unstructured":"Vladislav Lialin, Vijeta Deshpande, and Anna Rumshisky. 2023. Scaling down to scale up: A guide to parameter-efficient fine-tuning. arXiv preprint arXiv:2303.15647 (2023)."},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376590"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3328927"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569468"},{"key":"e_1_3_3_2_63_1","first-page":"93","article-title":"Lost in pruning: The effects of pruning neural networks beyond test accuracy","volume":"3","author":"Liebenwein Lucas","year":"2021","unstructured":"Lucas Liebenwein, Cenk Baykal, Brandon Carter, David Gifford, and Daniela Rus. 2021. Lost in pruning: The effects of pruning neural networks beyond test accuracy. Proceedings of Machine Learning and Systems 3 (2021), 93\u2013138.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2020.2986024"},{"key":"e_1_3_3_2_65_1","first-page":"1","article-title":"AdaSpring: Context-adaptive and runtime-evolutionary deep model compression for mobile applications","volume":"5","author":"Liu Sicong","year":"2021","unstructured":"Sicong Liu, Bin Guo, Ke Ma, Zhiwen Yu, and Junzhao Du. 2021. AdaSpring: Context-adaptive and runtime-evolutionary deep model compression for mobile applications. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, 1 (2021), 1\u201322.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_3_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512899"},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376445"},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"e_1_3_3_2_69_1","unstructured":"Microsoft. 2021. Neural network intelligence. https:\/\/github.com\/microsoft\/nni"},{"key":"e_1_3_3_2_70_1","volume-title":"Designing and training of lightweight neural networks on edge devices using early halting in knowledge distillation","author":"Mishra Rahul","year":"2023","unstructured":"Rahul Mishra and Hari\u00a0Prabhat Gupta. 2023. Designing and training of lightweight neural networks on edge devices using early halting in knowledge distillation. IEEE Transactions on Mobile Computing (2023)."},{"key":"e_1_3_3_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430450"},{"key":"e_1_3_3_2_72_1","volume-title":"Towards explainable deep learning for credit lending: A case study. arXiv","author":"Modarres Ceena","year":"2018","unstructured":"Ceena Modarres, Mark Ibrahim, Melissa Louie, and John Paisley. 2018. Towards explainable deep learning for credit lending: A case study. arXiv (2018)."},{"key":"e_1_3_3_2_73_1","doi-asserted-by":"publisher","DOI":"10.21428\/2c646de5.031d4553"},{"key":"e_1_3_3_2_74_1","volume-title":"Large language models shape and are shaped by society: A survey of arXiv publication patterns. arXiv preprint arXiv:2307.10700","author":"Movva Rajiv","year":"2023","unstructured":"Rajiv Movva, Sidhika Balachandar, Kenny Peng, Gabriel Agostini, Nikhil Garg, and Emma Pierson. 2023. Large language models shape and are shaped by society: A survey of arXiv publication patterns. arXiv preprint arXiv:2307.10700 (2023)."},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469029"},{"key":"e_1_3_3_2_76_1","unstructured":"NVIDIA. 2023. NVIDIA deep learning TensorRT documentation - optimizing TensorRT performance. https:\/\/docs.nvidia.com\/deeplearning\/tensorrt\/developer-guide\/index.html"},{"key":"e_1_3_3_2_77_1","volume-title":"Intriguing properties of compression on multilingual models. arXiv preprint arXiv:2211.02738","author":"Ogueji Kelechi","year":"2022","unstructured":"Kelechi Ogueji, Orevaoghene Ahia, Gbemileke Onilude, Sebastian Gehrmann, Sara Hooker, and Julia Kreutzer. 2022. Intriguing properties of compression on multilingual models. arXiv preprint arXiv:2211.02738 (2022)."},{"key":"e_1_3_3_2_78_1","volume-title":"International Conference on Machine Learning. PMLR, 1310\u20131318","author":"Pascanu Razvan","year":"2013","unstructured":"Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In International Conference on Machine Learning. PMLR, 1310\u20131318."},{"key":"e_1_3_3_2_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274405"},{"key":"e_1_3_3_2_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357160"},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449205"},{"key":"e_1_3_3_2_82_1","volume-title":"Model compression via distillation and quantization. arXiv","author":"Polino Antonio","year":"2018","unstructured":"Antonio Polino, Razvan Pascanu, and Dan Alistarh. 2018. Model compression via distillation and quantization. arXiv (2018). arXiv:1802.05668"},{"key":"e_1_3_3_2_83_1","unstructured":"PyTorch. 2018. Quantization. https:\/\/pytorch.org\/docs\/stable\/quantization.html"},{"key":"e_1_3_3_2_84_1","unstructured":"PyTorch. 2019. Sparisty. https:\/\/pytorch.org\/docs\/stable\/sparse.html"},{"key":"e_1_3_3_2_85_1","unstructured":"PyTorch. 2023. PyTorch Examples. https:\/\/pytorch.org\/tutorials\/"},{"key":"e_1_3_3_2_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449081"},{"key":"e_1_3_3_2_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445748"},{"key":"e_1_3_3_2_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_3_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"e_1_3_3_2_90_1","volume-title":"Organizational culture. Vol.\u00a045","author":"Schein H","unstructured":"Edgar\u00a0H Schein. 1990. Organizational culture. Vol.\u00a045. American Psychological Association."},{"key":"e_1_3_3_2_91_1","doi-asserted-by":"publisher","DOI":"10.3390\/make1010027"},{"key":"e_1_3_3_2_92_1","volume-title":"ICML Workshop on Vis for Deep Learning.","author":"Smilkov Daniel","year":"2016","unstructured":"Daniel Smilkov, Shan Carter, D Sculley, Fernanda\u00a0B Viegas, and Martin Wattenberg. 2016. Direct-manipulation visualization of deep networks. In ICML Workshop on Vis for Deep Learning."},{"key":"e_1_3_3_2_93_1","volume-title":"Evaluating the social impact of generative AI systems in systems and cociety. arXiv preprint arXiv:2306.05949","author":"Solaiman Irene","year":"2023","unstructured":"Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su\u00a0Lin Blodgett, Hal Daum\u00e9\u00a0III, Jesse Dodge, Ellie Evans, Sara Hooker, 2023. Evaluating the social impact of generative AI systems in systems and cociety. arXiv preprint arXiv:2306.05949 (2023)."},{"key":"e_1_3_3_2_94_1","unstructured":"Stanford. 2023. The AI index report: Measuring trends in artificial intelligence. https:\/\/aiindex.stanford.edu\/report\/"},{"key":"e_1_3_3_2_95_1","volume-title":"International Conference on Machine Learning. PMLR, 6105\u20136114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning. PMLR, 6105\u20136114. arXiv:1905.11946"},{"key":"e_1_3_3_2_96_1","unstructured":"TensorFlow. 2018. Introducing the Model Optimization Toolkit for TensorFlow. https:\/\/blog.tensorflow.org\/2018\/09\/introducing-model-optimization-toolkit.html"},{"key":"e_1_3_3_2_97_1","unstructured":"TensorFlow. 2020. Quantization aware training with TensorFlow Model Optimization Toolkit - performance with accuracy. https:\/\/blog.tensorflow.org\/2020\/04\/quantization-aware-training-with-tensorflow-model-optimization-toolkit.html"},{"key":"e_1_3_3_2_98_1","doi-asserted-by":"publisher","DOI":"10.1177\/1098214005283748"},{"key":"e_1_3_3_2_99_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15871-z"},{"key":"e_1_3_3_2_100_1","volume-title":"International Conference on Machine Learning. PMLR, 10347\u201310357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning. PMLR, 10347\u201310357."},{"key":"e_1_3_3_2_101_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00577"},{"key":"e_1_3_3_2_102_1","volume-title":"FastViT: A fast hybrid vision transformer using structural reparameterization. arXiv preprint arXiv:2303.14189","author":"Kumar\u00a0Anasosalu Vasu Pavan","year":"2023","unstructured":"Pavan Kumar\u00a0Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan. 2023. FastViT: A fast hybrid vision transformer using structural reparameterization. arXiv preprint arXiv:2303.14189 (2023)."},{"key":"e_1_3_3_2_103_1","unstructured":"Pavan Kumar\u00a0Anasosalu Vasu James Gabriel Jeff Zhu Oncel Tuzel and Anurag Ranjan. 2023. An improved one millisecond mobile backbone. (2023)."},{"key":"e_1_3_3_2_104_1","unstructured":"Pablo Villalobos Jaime Sevilla Tamay Besiroglu Lennart Heim Anson Ho and Marius Hobbhahn. 2022. Machine learning model sizes and the parameter gap. arxiv:2207.02852\u00a0[cs.LG]"},{"key":"e_1_3_3_2_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445526"},{"key":"e_1_3_3_2_106_1","volume-title":"How much automation does a data scientist want?arXiv","author":"Wang Dakuo","year":"2021","unstructured":"Dakuo Wang, Q\u00a0Vera Liao, Yunfeng Zhang, Udayan Khurana, Horst Samulowitz, Soya Park, Michael Muller, and Lisa Amini. 2021. How much automation does a data scientist want?arXiv (2021)."},{"key":"e_1_3_3_2_107_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359313"},{"key":"e_1_3_3_2_108_1","first-page":"1","article-title":"Genie in the model: Automatic generation of human-in-the-loop deep neural networks for mobile applications","volume":"7","author":"Wang Yanfei","year":"2023","unstructured":"Yanfei Wang, Zhiwen Yu, Sicong Liu, Zimu Zhou, and Bin Guo. 2023. Genie in the model: Automatic generation of human-in-the-loop deep neural networks for mobile applications. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 1 (2023), 1\u201329.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_3_2_109_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030418"},{"key":"e_1_3_3_2_110_1","volume-title":"Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers. O\u2019Reilly Media.","author":"Warden Pete","year":"2019","unstructured":"Pete Warden and Daniel Situnayake. 2019. Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers. O\u2019Reilly Media."},{"key":"e_1_3_3_2_111_1","unstructured":"Megan\u00a0Maher Welsh David Koski Miguel Sarabia Niv Sivakumar Ian Arawjo Aparna Joshi Moussa Doumbouya Luca Suau Xavierand\u00a0Zappella and Nicholas Apostoloff. 2023. Data and Network Introspection Kit. https:\/\/github.com\/apple\/dnikit"},{"key":"e_1_3_3_2_112_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501943"},{"key":"e_1_3_3_2_113_1","volume-title":"Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining, Vol.\u00a01. Manchester, 29\u201339","author":"Wirth R\u00fcdiger","year":"2000","unstructured":"R\u00fcdiger Wirth and Jochen Hipp. 2000. CRISP-DM: Towards a standard process model for data mining. In Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining, Vol.\u00a01. Manchester, 29\u201339."},{"key":"e_1_3_3_2_114_1","volume-title":"Workshop on Trust and Expertise in Visual Analytics at IEEE VIS","author":"Wright P.","year":"2020","unstructured":"Austin\u00a0P. Wright, Zijie\u00a0J. Wang, Haekyu Park, Grace Guo, Fabian Sperrle, Mennatallah El-Assady, Alex Endert, Daniel Keim, and Duen\u00a0Horng Chau. 2020. A comparative analysis of industry human-AI interaction guidelines. Workshop on Trust and Expertise in Visual Analytics at IEEE VIS (2020)."},{"key":"e_1_3_3_2_115_1","volume-title":"International Conference on Machine Learning. PMLR, 5363\u20135372","author":"Wu Junru","year":"2018","unstructured":"Junru Wu, Yue Wang, Zhenyu Wu, Zhangyang Wang, Ashok Veeraraghavan, and Yingyan Lin. 2018. Deep k-means: Re-training and parameter sharing with harder cluster assignments for compressing deep convolutions. In International Conference on Machine Learning. PMLR, 5363\u20135372."},{"key":"e_1_3_3_2_116_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26255"},{"key":"e_1_3_3_2_117_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501904"},{"key":"e_1_3_3_2_118_1","volume-title":"AAAI Spring Symposium Series.","author":"Yang Qian","year":"2018","unstructured":"Qian Yang. 2018. Machine learning as a UX design material: How can we imagine beyond automation, recommenders, and reminders?. In AAAI Spring Symposium Series."},{"key":"e_1_3_3_2_119_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196709.3196730"},{"key":"e_1_3_3_2_120_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479535"},{"key":"e_1_3_3_2_121_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517491"},{"key":"e_1_3_3_2_122_1","doi-asserted-by":"publisher","DOI":"10.1109\/icicis46948.2019.9014733"},{"key":"e_1_3_3_2_123_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517607"},{"key":"e_1_3_3_2_124_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392826"},{"key":"e_1_3_3_2_125_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00716"},{"key":"e_1_3_3_2_126_1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2022.3153408"},{"key":"e_1_3_3_2_127_1","volume-title":"A survey of large language models. arXiv preprint arXiv:2303.18223","author":"Zhao Wayne\u00a0Xin","year":"2023","unstructured":"Wayne\u00a0Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_3_2_128_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472630"},{"key":"e_1_3_3_2_129_1","doi-asserted-by":"publisher","DOI":"10.1145\/3464941"},{"key":"e_1_3_3_2_130_1","volume-title":"A comprehensive survey on pretrained foundation models: A history from BERT to ChatGPT. arXiv preprint arXiv:2302.09419","author":"Zhou Ce","year":"2023","unstructured":"Ce Zhou, Qian Li, Chen Li, Jun Yu, Yixin Liu, Guangjing Wang, Kai Zhang, Cheng Ji, Qiben Yan, Lifang He, 2023. A comprehensive survey on pretrained foundation models: A history from BERT to ChatGPT. arXiv preprint arXiv:2302.09419 (2023)."},{"key":"e_1_3_3_2_131_1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2019.2918951"},{"key":"e_1_3_3_2_132_1","first-page":"27319","article-title":"Dynamic resolution network","volume":"34","author":"Zhu Mingjian","year":"2021","unstructured":"Mingjian Zhu, Kai Han, Enhua Wu, Qiulin Zhang, Ying Nie, Zhenzhong Lan, and Yunhe Wang. 2021. Dynamic resolution network. Advances in Neural Information Processing Systems 34 (2021), 27319\u201327330. arXiv:2106.02898","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642109","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:41Z","timestamp":1750291001000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":132,"alternative-id":["10.1145\/3613904.3642109","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642109","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}