{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:43:51Z","timestamp":1760057031526,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SR-2402328, CAREER-2338457, CSR-2406069, CSR-2323100, HRD-2225201, CCF-1718335, CNS-1956229, IIS- 233190"],"award-info":[{"award-number":["SR-2402328, CAREER-2338457, CSR-2406069, CSR-2323100, HRD-2225201, CCF-1718335, CNS-1956229, IIS- 233190"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016822","name":"Seagate Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016822","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016299","name":"NetApp","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016299","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3757347.3759139","type":"proceedings-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T16:24:42Z","timestamp":1756398282000},"page":"16-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LATTICE: Efficient In-Memory DNN Model Versioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1120-2337","authenticated-orcid":false,"given":"Manoj P.","family":"Saha","sequence":"first","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9695-8011","authenticated-orcid":false,"given":"Ashikee","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5243-9451","authenticated-orcid":false,"given":"Raju","family":"Rangaswami","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8761-5486","authenticated-orcid":false,"given":"Yanzhao","family":"Wu","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4421-9923","authenticated-orcid":false,"given":"Janki","family":"Bhimani","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. ZIP (file format). https:\/\/en.wikipedia.org\/wiki\/ZIP_(file_format)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3465402"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3644815.3644965"},{"key":"e_1_3_2_1_4_1","volume-title":"Freezeout: Accelerate training by progressively freezing layers. arXiv preprint arXiv:1706.04983","author":"Brock Andrew","year":"2017","unstructured":"Andrew Brock, Theodore Lim, James M Ritchie, and Nick Weston. 2017. Freezeout: Accelerate training by progressively freezing layers. arXiv preprint arXiv:1706.04983 (2017)."},{"key":"e_1_3_2_1_5_1","unstructured":"Andrew Brock Theodore Lim J. M. Ritchie and Nick Weston. 2017. FreezeOut: Accelerate Training by Progressively Freezing Layers. arXiv:1706.04983 [stat.ML] https:\/\/arxiv.org\/abs\/1706.04983"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD58817.2023.00031"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525090"},{"key":"e_1_3_2_1_8_1","volume-title":"Non-Volatile Memories. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS XVI).","author":"Coburn Joel","year":"2011","unstructured":"Joel Coburn, Adrian Caulfield, Ameen Akel, Laura Grupp, Rajesh Gupta, Ranjit Jhala, and Steven Swanson. 2011. NV-Heaps: Making Persistent Objects Fast and Safe With Next-Generation, Non-Volatile Memories. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS XVI)."},{"key":"e_1_3_2_1_9_1","unstructured":"CXL Consortium. [n. d.]. Compute Express Link. https:\/\/computeexpresslink.org\/"},{"key":"e_1_3_2_1_10_1","unstructured":"Intel Corporation. [n. d.]. eADR: New Opportunities for Persistent Memory Applications. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/eadr-new-opportunities-for-persistent-memory-applications.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.62"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML59370.2024.00036"},{"key":"e_1_3_2_1_13_1","volume-title":"Symposium on Networked Systems Design and Implementation.","author":"Eisenman Assaf","year":"2020","unstructured":"Assaf Eisenman, Kiran Kumar Matam, Steven Ingram, Dheevatsa Mudigere, Raghuraman Krishnamoorthi, Krishnakumar Nair, Mikhail Smelyanskiy, and Murali Annavaram. 2020. Check-N-Run: a Checkpointing System for Training Deep Learning Recommendation Models. In Symposium on Networked Systems Design and Implementation."},{"key":"e_1_3_2_1_14_1","unstructured":"GitHub. [n.d.]. Git large File Storage. https:\/\/git-lfs.com\/"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"volume-title":"Get M for Free. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJYwwY9ll","author":"Huang Gao","key":"e_1_3_2_1_16_1","unstructured":"Gao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu, John E. Hopcroft, and Kilian Q. Weinberger. 2017. Snapshot Ensembles: Train 1, Get M for Free. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJYwwY9ll"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Huang Gao","key":"e_1_3_2_1_18_1","unstructured":"Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_19_1","unstructured":"SK Hynix. [n. d.]. How Selector-Only Memory Emerged as the Leading Solution for CXL. https:\/\/news.skhynix.com\/how-selector-only-memory-emerged-as-the-leading-solution-for-cxl\/"},{"key":"e_1_3_2_1_20_1","unstructured":"Hongpeng Jin Wenqi Wei Xuyu Wang Wenbin Zhang and Yanzhao Wu. 2023. Rethinking Learning Rate Tuning in the Era of Large Language Models. arXiv:2309.08859 [cs.LG]"},{"key":"e_1_3_2_1_21_1","volume-title":"TENET: Memory Safe and Fault Tolerant Persistent Transactional Memory. In 21st USENIX Conference on File and Storage Technologies (FAST 23)","author":"Krishnan R. Madhava","year":"2023","unstructured":"R. Madhava Krishnan, Diyu Zhou, Wook-Hee Kim, Sudarsun Kannan, Sanidhya Kashyap, and Changwoo Min. 2023. TENET: Memory Safe and Fault Tolerant Persistent Transactional Memory. In 21st USENIX Conference on File and Storage Technologies (FAST 23). USENIX Association, Santa Clara, CA, 247--264. https:\/\/www.usenix.org\/conference\/fast23\/presentation\/krishnan"},{"key":"e_1_3_2_1_22_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"volume-title":"Advances in Neural Information Processing Systems 25","author":"Krizhevsky Alex","key":"e_1_3_2_1_23_1","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 1097--1105. http:\/\/papers.nips.cc\/paper\/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00015"},{"key":"e_1_3_2_1_25_1","volume-title":"Deep Reinforcement Learning Based Multi-Task Automated Channel Pruning for DNNs. In 2023 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--9.","author":"Ma Xiaodong","year":"2023","unstructured":"Xiaodong Ma and Weiwei Fang. 2023. Deep Reinforcement Learning Based Multi-Task Automated Channel Pruning for DNNs. In 2023 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--9."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of Machine Learning and Systems, A. Smola, A. Dimakis, and I. Stoica (Eds.)","volume":"3","author":"Maeng Kiwan","year":"2021","unstructured":"Kiwan Maeng, Shivam Bharuka, Isabel Gao, Mark Jeffrey, Vikram Saraph, Bor-Yiing Su, Caroline Trippel, Jiyan Yang, Mike Rabbat, Brandon Lucia, and Carole-Jean Wu. 2021. Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery. In Proceedings of Machine Learning and Systems, A. Smola, A. Dimakis, and I. Stoica (Eds.), Vol. 3. 637--651. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2021\/file\/f09e98bc2e2f0abc3e315eaa0d808fc-Paper.pdf"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278141"},{"key":"e_1_3_2_1_28_1","volume-title":"Fine-Grained DNN Checkpointing. In USENIX Conference on File and Storage Technologies.","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In USENIX Conference on File and Storage Technologies."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-76"},{"key":"e_1_3_2_1_30_1","unstructured":"OpenMP. [n. d.]. https:\/\/www.openmp.org\/."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507758"},{"key":"e_1_3_2_1_32_1","unstructured":"Pmem.io. [n. d.]. Persistent Memory Programming. http:\/\/pmem.io."},{"key":"e_1_3_2_1_33_1","unstructured":"Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. http:\/\/pjreddie.com\/darknet\/."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767"},{"key":"e_1_3_2_1_35_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems 27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6105--6114. https:\/\/proceedings.mlr.press\/v97\/tan19a.html"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196934"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939502.2939516"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950365.1950379"},{"key":"e_1_3_2_1_41_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Wang Feng","year":"2021","unstructured":"Feng Wang, Guoyizhe Wei, Qiao Liu, Jinxiang Ou, xian wei, and Hairong Lv. 2021. Boost Neural Networks by Checkpoints. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 19719--19729. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/a40511cad8383e5ae8ddd8b855d135da-Paper.pdf"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCDS53736.2022.9760959"},{"key":"e_1_3_2_1_44_1","unstructured":"Martin Wistuba Ambrish Rawat and Tejaswini Pedapati. 2019. A Survey on Neural Architecture Search. arXiv:1905.01392 [cs.LG]"},{"key":"e_1_3_2_1_45_1","first-page":"39","article-title":"Accelerating the Machine Learning Lifecycle with MLflow","volume":"41","author":"Zaharia Matei A.","year":"2018","unstructured":"Matei A. Zaharia, Andrew Chen, Aaron Davidson, Ali Ghodsi, Sue Ann Hong, Andy Konwinski, Siddharth Murching, Tomas Nykodym, Paul Ogilvie, Mani Parkhe, Fen Xie, and Corey Zumar. 2018. Accelerating the Machine Learning Lifecycle with MLflow. IEEE Data Eng. Bull. 41 (2018), 39--45. https:\/\/api.semanticscholar.org\/CorpusID:83459546","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_46_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric. P Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arXiv:2306.05685 [cs.CL]"},{"key":"e_1_3_2_1_47_1","volume-title":"SWIFT: Expedited Failure Recovery for Large-scale DNN Training. arXiv:2302.06173 [cs.DC]","author":"Zhong Yuchen","year":"2023","unstructured":"Yuchen Zhong, Guangming Sheng, Juncheng Liu, Jinhui Yuan, and Chuan Wu. 2023. SWIFT: Expedited Failure Recovery for Large-scale DNN Training. arXiv:2302.06173 [cs.DC]"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"}],"event":{"name":"SYSTOR '25: The 18th ACM International Systems and Storage Conference","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","Technion Israel Institute of Technology"],"location":"Virtual Israel","acronym":"SYSTOR '25"},"container-title":["Proceedings of the 18th ACM International Systems and Storage Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757347.3759139","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757347.3759139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T14:13:14Z","timestamp":1760019194000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757347.3759139"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":48,"alternative-id":["10.1145\/3757347.3759139","10.1145\/3757347"],"URL":"https:\/\/doi.org\/10.1145\/3757347.3759139","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-09-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}