{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:42:29Z","timestamp":1775068949370,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1145\/3639477.3639716","type":"proceedings-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T13:27:26Z","timestamp":1717162046000},"page":"323-333","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A New Frontier of AI: On-Device AI Training and Personalization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0888-2143","authenticated-orcid":false,"given":"Jijoong","family":"Moon","sequence":"first","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3823-4080","authenticated-orcid":false,"given":"Hyeonseok","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2884-4474","authenticated-orcid":false,"given":"Jiho","family":"Chu","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3486-787X","authenticated-orcid":false,"given":"Donghak","family":"Park","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9249-4890","authenticated-orcid":false,"given":"Seungbaek","family":"Hong","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8956-0473","authenticated-orcid":false,"given":"Hyungjun","family":"Seo","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1269-3785","authenticated-orcid":false,"given":"Donghyeon","family":"Jeong","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5730-1302","authenticated-orcid":false,"given":"Sungsik","family":"Kong","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9731-0253","authenticated-orcid":false,"given":"Myungjoo","family":"Ham","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,31]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). USENIX Association, Savannah, GA, 265--283. https:\/\/www.usenix.org\/conference\/osdi16\/technical-sessions\/presentation\/abadi"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1971.10488811"},{"key":"e_1_3_2_1_3_1","volume-title":"Alexey Andreyevich Radul, and Jeffrey Mark Siskind","author":"Baydin Atilim Gunes","year":"2018","unstructured":"Atilim Gunes Baydin, Barak A Pearlmutter, Alexey Andreyevich Radul, and Jeffrey Mark Siskind. 2018. Automatic differentiation in machine learning: a survey. Journal of machine learning research 18 (2018)."},{"key":"e_1_3_2_1_4_1","unstructured":"Yaroslav Bulatov. 2018. Fitting larger networks into memory. https:\/\/medium.com\/tensorflow\/fitting-larger-networks-into-memory-583e3c758ff9."},{"key":"e_1_3_2_1_5_1","volume-title":"Tinytl: Reduce memory, not parameters for efficient on-device learning. arXiv preprint arXiv:2007.11622","author":"Cai Han","year":"2020","unstructured":"Han Cai, Chuang Gan, Ligeng Zhu, and Song Han. 2020. Tinytl: Reduce memory, not parameters for efficient on-device learning. arXiv preprint arXiv:2007.11622 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_8_1","volume-title":"A continual learning survey: Defying forgetting in classification tasks","author":"Delange Matthias","year":"2021","unstructured":"Matthias Delange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ales Leonardis, Greg Slabaugh, and Tinne Tuytelaars. 2021. A continual learning survey: Defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"The indirect convolution algorithm. arXiv preprint arXiv:1907.02129","author":"Dukhan Marat","year":"2019","unstructured":"Marat Dukhan. 2019. The indirect convolution algorithm. arXiv preprint arXiv:1907.02129 (2019)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2009.12.010"},{"key":"e_1_3_2_1_11_1","unstructured":"Google. 2018. TensorFlow-Lite. https:\/\/www.tensorflow.org\/lite."},{"key":"e_1_3_2_1_12_1","volume-title":"NNStreamer: Efficient and Agile Development of On-Device AI Systems. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","author":"Ham MyungJoo","unstructured":"MyungJoo Ham, Jijoong Moon, Geunsik Lim, Jaeyun Jung, Hyoungjoo Ahn, Wook Song, Sangjung Woo, Parichay Kapoor, Dongju Chae, Gichan Jang, Yongjoo Ahn, and Jihoon Lee. 2021. NNStreamer: Efficient and Agile Development of On-Device AI Systems. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 198--207."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Geoffrey Hinton Li Deng Dong Yu George E Dahl Abdel-rahman Mohamed Navdeep Jaitly Andrew Senior Vincent Vanhoucke Patrick Nguyen Tara N Sainath et al. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing magazine 29 6 (2012) 82--97.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_2_1_15_1","volume-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism. Advances in neural information processing systems 32","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, et al. 2019. Gpipe: Efficient training of giant neural networks using pipeline parallelism. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_18_1","unstructured":"Justin Basilico. 2021. Netflix Explains Recommendations and Personalization. http:https:\/\/scale.com\/blog\/Netflix-Recommendation-Personalization-TransformX-Scale-AI-Insights."},{"key":"e_1_3_2_1_19_1","volume-title":"Deep learning with Python","author":"Ketkar Nikhil","unstructured":"Nikhil Ketkar. 2017. Stochastic gradient descent. In Deep learning with Python. Springer, 113--132."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_21_1","volume-title":"A review of applications in federated learning. Computers & Industrial Engineering","author":"Li Li","year":"2020","unstructured":"Li Li, Yuxi Fan, Mike Tse, and Kuo-Yi Lin. 2020. A review of applications in federated learning. Computers & Industrial Engineering (2020), 106854."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP52600.2021.00009"},{"key":"e_1_3_2_1_23_1","volume-title":"SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices. In MobiCom 2023 (Annual International Conference On Mobile Computing And Networking), To appear.","author":"Lim Geunsik","year":"2023","unstructured":"Geunsik Lim, Donghyun Kang, MyungJoo Ham, and Young Ik Eom. 2023. SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices. In MobiCom 2023 (Annual International Conference On Mobile Computing And Networking), To appear."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.01.010"},{"key":"e_1_3_2_1_26_1","volume-title":"d.]. On-Device AI. https:\/\/www.technologyreview.com\/hub\/ubiquitous-on-device-ai\/. (accessed","author":"Technical Review MIT","year":"2021","unstructured":"MIT Technical Review. [n. d.]. On-Device AI. https:\/\/www.technologyreview.com\/hub\/ubiquitous-on-device-ai\/. (accessed 14 Dec 2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning. PMLR, 4646--4655","author":"Mostafa Hesham","year":"2019","unstructured":"Hesham Mostafa and Xin Wang. 2019. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In International Conference on Machine Learning. PMLR, 4646--4655."},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. 6th Int. Conf. on Learning Representations (ICLR).","author":"Narang Sharan","year":"2018","unstructured":"Sharan Narang, Gregory Diamos, Erich Elsen, Paulius Micikevicius, Jonah Alben, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, et al. 2018. Mixed precision training. In Proc. 6th Int. Conf. on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_29_1","unstructured":"ndevilla. 2017. Iniparser4. https:\/\/github.com\/ndevilla\/iniparser."},{"key":"e_1_3_2_1_30_1","volume-title":"A review on image segmentation techniques. Pattern recognition 26, 9","author":"Pal Nikhil R","year":"1993","unstructured":"Nikhil R Pal and Sankar K Pal. 1993. A review on image segmentation techniques. Pattern recognition 26, 9 (1993), 1277--1294."},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on machine learning. PMLR, 1310--1318","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--1318."},{"key":"e_1_3_2_1_32_1","volume-title":"NIPS 2017 Workshop on Autodiff","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in pytorch. In NIPS 2017 Workshop on Autodiff (Long Beach, California, USA). https:\/\/openreview.net\/forum?id=BJJsrmfCZ"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"e_1_3_2_1_35_1","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. {ZeRO-Offload}: Democratizing {Billion-Scale} Model Training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 551--564."},{"key":"e_1_3_2_1_36_1","volume-title":"Memory optimization for deep networks. arXiv preprint arXiv:2010.14501","author":"Shah Aashaka","year":"2020","unstructured":"Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, and Philipp Kr\u00e4henb\u00fchl. 2020. Memory optimization for deep networks. arXiv preprint arXiv:2010.14501 (2020)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_38_1","volume-title":"Jaehong Kim, and Jiwon Kim.","author":"Shin Hanul","year":"2017","unstructured":"Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual learning with deep generative replay. arXiv preprint arXiv:1705.08690 (2017)."},{"key":"e_1_3_2_1_39_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_42_1","volume-title":"Lifelong robot learning. Robotics and autonomous systems 15, 1-2","author":"Thrun Sebastian","year":"1995","unstructured":"Sebastian Thrun and Tom M Mitchell. 1995. Lifelong robot learning. Robotics and autonomous systems 15, 1-2 (1995), 25--46."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Lisa Torrey and Jude Shavlik. 2010. Transfer learning. In Handbook of research on machine learning applications and trends: algorithms methods and techniques. IGI global 242--264.","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"e_1_3_2_1_44_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57959-7"},{"key":"e_1_3_2_1_46_1","volume-title":"A learning algorithm for continually running fully recurrent neural networks. Neural computation 1, 2","author":"Williams Ronald J","year":"1989","unstructured":"Ronald J Williams and David Zipser. 1989. A learning algorithm for continually running fully recurrent neural networks. Neural computation 1, 2 (1989), 270--280."},{"key":"e_1_3_2_1_47_1","volume-title":"Deep image: Scaling up image recognition. arXiv preprint arXiv:1501.02876 7, 8","author":"Wu Ren","year":"2015","unstructured":"Ren Wu, Shengen Yan, Yi Shan, Qingqing Dang, and Gang Sun. 2015. Deep image: Scaling up image recognition. arXiv preprint arXiv:1501.02876 7, 8 (2015)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2919431"},{"key":"e_1_3_2_1_49_1","first-page":"15511","article-title":"Improved analysis of clipping algorithms for non-convex optimization","volume":"33","author":"Zhang Bohang","year":"2020","unstructured":"Bohang Zhang, Jikai Jin, Cong Fang, and Liwei Wang. 2020. Improved analysis of clipping algorithms for non-convex optimization. Advances in Neural Information Processing Systems 33 (2020), 15511--15521.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","volume-title":"http:https:\/\/github.com\/xianyi\/OpenBLAS. accepted","author":"Xianyi Zhang","year":"2023","unstructured":"Zhang Xianyi. 2013. OpenBLAS. http:https:\/\/github.com\/xianyi\/OpenBLAS. accepted 21 Dec 2023"}],"event":{"name":"ICSE-SEIP '24: 46th International Conference on Software Engineering: Software Engineering in Practice","location":"Lisbon Portugal","acronym":"ICSE-SEIP '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639477.3639716","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3639477.3639716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:31Z","timestamp":1750290271000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639477.3639716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":50,"alternative-id":["10.1145\/3639477.3639716","10.1145\/3639477"],"URL":"https:\/\/doi.org\/10.1145\/3639477.3639716","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]},"assertion":[{"value":"2024-05-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}