{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:39:55Z","timestamp":1766219995977,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["2023YFB4502801"],"award-info":[{"award-number":["2023YFB4502801"]}]},{"name":"National Natural Science Foundation of China","award":["U22A2027"],"award-info":[{"award-number":["U22A2027"]}]},{"name":"National Natural Science Foundation of China","award":["62402187"],"award-info":[{"award-number":["62402187"]}]},{"name":"China Postdoctoral Science Foundation","award":["GZB20240243"],"award-info":[{"award-number":["GZB20240243"]}]},{"name":"China Postdoctoral Science Foundation","award":["2024M751009"],"award-info":[{"award-number":["2024M751009"]}]},{"name":"Postdoctoral Project of Hubei Province","award":["2024HBBHCXA024"],"award-info":[{"award-number":["2024HBBHCXA024"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3754598.3754672","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:34:32Z","timestamp":1766219672000},"page":"320-330","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SpiderCache: Semantic-Aware Caching Strategy for DNN Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6718-6557","authenticated-orcid":false,"given":"Zesong","family":"Wang","sequence":"first","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4741-9282","authenticated-orcid":false,"given":"Peng","family":"Fang","sequence":"additional","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2791-4158","authenticated-orcid":false,"given":"Fang","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1477-9751","authenticated-orcid":false,"given":"Hong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1796-3831","authenticated-orcid":false,"given":"Yimin","family":"Lu","sequence":"additional","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7798-1121","authenticated-orcid":false,"given":"Zhan","family":"Shi","sequence":"additional","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4674-6006","authenticated-orcid":false,"given":"Dan","family":"Feng","sequence":"additional","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00108"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Stephen Balaban. 2015. Deep learning and face recognition: the state of the art. Biometric and surveillance technology for human and activity identification XII 9457 (2015) 68\u201375.","DOI":"10.1117\/12.2181526"},{"key":"e_1_3_3_1_4_2","unstructured":"Peter\u00a0W Battaglia Jessica\u00a0B Hamrick Victor Bapst Alvaro Sanchez-Gonzalez Vinicius Zambaldi Mateusz Malinowski Andrea Tacchetti David Raposo Adam Santoro Ryan Faulkner et\u00a0al. 2018. Relational inductive biases deep learning and graph networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1806.01261 (2018)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Yoshua Bengio Aaron Courville and Pascal Vincent. 2013. Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence 35 8 (2013) 1798\u20131828.","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_3_1_6_2","unstructured":"Mariusz Bojarski. 2016. End to end learning for self-driving cars. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1604.07316 (2016)."},{"key":"e_1_3_3_1_7_2","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et\u00a0al. 2018. { TVM} : An automated { End-to-End} optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 578\u2013594."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1109\/HPCA56546.2023.10070964","volume-title":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","author":"Chen Weijian","year":"2023","unstructured":"Weijian Chen, Shuibing He, Yaowen Xu, Xuechen Zhang, Siling Yang, Shuang Hu, Xian-He Sun, and Gang Chen. 2023. icache: An importance-sampling-informed cache for accelerating i\/o-bound dnn model training. In 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 220\u2013232."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Xue-Wen Chen and Xiaotong Lin. 2014. Big data deep learning: challenges and perspectives. IEEE access 2 (2014) 514\u2013525.","DOI":"10.1109\/ACCESS.2014.2325029"},{"key":"e_1_3_3_1_10_2","volume-title":"Proceedings of the 2021 ACM SIGMOD International Conference on Management of Data","author":"Chen Zhe","year":"2021","unstructured":"Zhe Chen, Bolin Ding, and et al.2021. SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search. In Proceedings of the 2021 ACM SIGMOD International Conference on Management of Data. https:\/\/www.microsoft.com\/en-us\/research\/publication\/spann-highly-efficient-billion-scale-approximate-nearest-neighbor-search\/"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/Cluster48925.2021.00097","volume-title":"2021 IEEE International Conference on Cluster Computing (CLUSTER)","author":"Dantas Marco","year":"2021","unstructured":"Marco Dantas, Diogo Leitao, Cl\u00e1udia Correia, Ricardo Macedo, Weijia Xu, and Joao Paulo. 2021. Monarch: Hierarchical storage management for deep learning frameworks. In 2021 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 657\u2013663."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_13_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Andre Esteva Brett Kuprel Roberto\u00a0A Novoa Justin Ko Susan\u00a0M Swetter Helen\u00a0M Blau and Sebastian Thrun. 2017. Dermatologist-level classification of skin cancer with deep neural networks. nature 542 7639 (2017) 115\u2013118.","DOI":"10.1038\/nature21056"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_3_1_16_2","unstructured":"Will Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_17_2","unstructured":"Sayed\u00a0Hadi Hashemi Sangeetha Abdu\u00a0Jyothi and Roy Campbell. 2019. Tictac: Accelerating distributed deep learning with communication scheduling. Proceedings of Machine Learning and Systems 1 (2019) 418\u2013430."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_3_1_20_2","unstructured":"Paras Jain Xiangxi Mo Ajay Jain Harikaran Subbaraj Rehan\u00a0Sohail Durrani Alexey Tumanov Joseph Gonzalez and Ion Stoica. 2018. Dynamic space-time scheduling for gpu inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1901.00041 (2018) 1\u20138."},{"key":"e_1_3_3_1_21_2","unstructured":"Angela\u00a0H Jiang Daniel L-K Wong Giulio Zhou David\u00a0G Andersen Jeffrey Dean Gregory\u00a0R Ganger Gauri Joshi Michael Kaminksy Michael Kozuch Zachary\u00a0C Lipton et\u00a0al. 2019. Accelerating deep learning by focusing on the biggest losers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1910.00762 (2019)."},{"key":"e_1_3_3_1_22_2","unstructured":"Tyler\u00a0B Johnson and Carlos Guestrin. 2018. Training deep models faster with robust approximate importance sampling. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_3_1_23_2","first-page":"135","volume-title":"21st USENIX Conference on File and Storage Technologies (FAST 23)","author":"Khan Redwan Ibne\u00a0Seraj","year":"2023","unstructured":"Redwan Ibne\u00a0Seraj Khan, Ahmad\u00a0Hossein Yazdani, Yuqi Fu, Arnab\u00a0K Paul, Bo Ji, Xun Jian, Yue Cheng, and Ali\u00a0R Butt. 2023. { SHADE} : Enable Fundamental Cacheability for Distributed Deep Learning Training. In 21st USENIX Conference on File and Storage Technologies (FAST 23). 135\u2013152."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Ana Klimovic Heiner Litz and Christos Kozyrakis. 2017. Reflex: Remote flash \u2248 local flash. ACM SIGARCH Computer Architecture News 45 1 (2017) 345\u2013359.","DOI":"10.1145\/3093337.3037732"},{"key":"e_1_3_3_1_25_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_3_1_26_2","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey\u00a0E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_3_1_27_2","first-page":"283","volume-title":"18th USENIX Conference on File and Storage Technologies (FAST 20)","author":"Kumar Abhishek\u00a0Vijaya","year":"2020","unstructured":"Abhishek\u00a0Vijaya Kumar and Muthian Sivathanu. 2020. Quiver: An informed storage cache for deep learning. In 18th USENIX Conference on File and Storage Technologies (FAST 20). 283\u2013296."},{"key":"e_1_3_3_1_28_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2015. Online batch selection for faster training of neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1511.06343 (2015)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Yu\u00a0A Malkov and Dmitry\u00a0A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence 42 4 (2018) 824\u2013836.","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_3_1_30_2","unstructured":"Tomas Mikolov. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1301.3781 3781 (2013)."},{"key":"e_1_3_3_1_31_2","unstructured":"Jayashree Mohan Amar Phanishayee Ashish Raniwala and Vijay Chidambaram. 2020. Analyzing and mitigating data stalls in DNN training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2007.06775 (2020)."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Yosuke Oyama Naoya Maruyama Nikoli Dryden Erin McCarthy Peter Harrington Jan Balewski Satoshi Matsuoka Peter Nugent and Brian Van\u00a0Essen. 2020. The case for strong scaling in deep learning: Training large 3d cnns with hybrid parallelism. IEEE Transactions on Parallel and Distributed Systems 32 7 (2020) 1641\u20131652.","DOI":"10.1109\/TPDS.2020.3047974"},{"key":"e_1_3_3_1_33_2","unstructured":"Christian Pinto Yiannis Gkoufas Andrea Reale Seetharami Seelam and Steven Eliuk. 2018. Hoard: A distributed data caching system to accelerate deep learning training on the cloud. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.00669 (2018)."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195660"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3211346.3211348"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Abraham Savitzky and Marcel\u00a0JE Golay. 1964. Smoothing and differentiation of data by simplified least squares procedures. Analytical chemistry 36 8 (1964) 1627\u20131639.","DOI":"10.1021\/ac60214a047"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Connor Shorten and Taghi\u00a0M Khoshgoftaar. 2019. A survey on image data augmentation for deep learning. Journal of big data 6 1 (2019) 1\u201348.","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_3_1_39_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556 (2014)."},{"key":"e_1_3_3_1_40_2","unstructured":"Yifan Tan Zheng Liu Mingmin Ge and et al.2022. FINGER: Fast Inference for Graph-Based Approximate Nearest Neighbor Search. Amazon Science (2022). https:\/\/www.amazon.science\/publications\/finger-fast-inference-for-graph-based-approximate-nearest-neighbor-search"},{"key":"e_1_3_3_1_41_2","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Jason Wang Luis Perez et\u00a0al. 2017. The effectiveness of data augmentation in image classification using deep learning. Convolutional Neural Networks Vis. Recognit 11 2017 (2017) 1\u20138.","DOI":"10.1109\/ICSPCC.2017.8242527"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404472"},{"key":"e_1_3_3_1_44_2","unstructured":"Suorong Yang Weikang Xiao Mengchen Zhang Suhan Guo Jian Zhao and Furao Shen. 2022. Image data augmentation for deep learning: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.08610 (2022)."},{"key":"e_1_3_3_1_45_2","unstructured":"Jiong Zhang Hsiang-Fu Yu and Inderjit\u00a0S Dhillon. 2019. Autoassist: A framework to accelerate training of deep neural networks. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1109\/IPDPS47924.2020.00050","volume-title":"2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","author":"Zhang Zhao","year":"2020","unstructured":"Zhao Zhang, Lei Huang, J\u00a0Gregory Pauloski, and Ian\u00a0T Foster. 2020. Efficient I\/O for neural network training with compressed data. In 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 409\u2013418."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2018.00023"},{"key":"e_1_3_3_1_48_2","first-page":"1","volume-title":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","author":"Zhu Yue","year":"2019","unstructured":"Yue Zhu, Weikuan Yu, Bing Jiao, Kathryn Mohror, Adam Moody, and Fahim Chowdhury. 2019. Efficient user-level storage disaggregation for deep learning. In 2019 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 1\u201312."}],"event":{"name":"ICPP '25: 54th International Conference on Parallel Processing","location":"San Diego CA USA","acronym":"ICPP '25"},"container-title":["Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754598.3754672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:37:46Z","timestamp":1766219866000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754598.3754672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":47,"alternative-id":["10.1145\/3754598.3754672","10.1145\/3754598"],"URL":"https:\/\/doi.org\/10.1145\/3754598.3754672","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}