{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:42Z","timestamp":1786120842794,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62502430"],"award-info":[{"award-number":["62502430"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ26F020004"],"award-info":[{"award-number":["LQ26F020004"]}]},{"name":"ByteDance Research Project","award":["CT20250218122839"],"award-info":[{"award-number":["CT20250218122839"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818410","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"8399-8409","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FLEDA: Forecasting-Based Data Partition Placement for Efficient Deep Learning Recommendation Model Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9032-195X","authenticated-orcid":false,"given":"Yuchen","family":"Yang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4494-3081","authenticated-orcid":false,"given":"Teng","family":"Yin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5575-6465","authenticated-orcid":false,"given":"Yang","family":"Guo","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5358-4523","authenticated-orcid":false,"given":"Qingheng","family":"Gao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5629-1705","authenticated-orcid":false,"given":"Jixi","family":"Shan","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9871-503X","authenticated-orcid":false,"given":"Hang","family":"Cheng","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4443-1555","authenticated-orcid":false,"given":"Xiuqi","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2610-3490","authenticated-orcid":false,"given":"Jun","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9122-4703","authenticated-orcid":false,"given":"Rui","family":"Shi","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8365-4741","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"FlashNeuron: SSD-Enabled Large-Batch Training of Very Deep Neural Networks. In USENIX Conference on File and Storage Technologies (FAST). USENIX Association, 387-401","author":"Bae Jonghyun","unstructured":"Jonghyun Bae, Jongsung Lee, Yunho Jin, Sam Son, Shine Kim, Hakbeom Jang, Tae Jun Ham, and Jae W. Lee. 2021. FlashNeuron: SSD-Enabled Large-Batch Training of Very Deep Neural Networks. In USENIX Conference on File and Storage Technologies (FAST). USENIX Association, 387-401. https:\/\/www.usenix.org\/conference\/fast21\/presentation\/bae"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3155196"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578354.3592865"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30637-2_37"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.06053"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070964"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00076"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736938"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476181"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709177"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33271"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"e_1_3_2_2_13_1","volume-title":"TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting. In International Conference on Machine Learning (ICML). PMLR. https:\/\/proceedings.mlr.press\/v267\/hu25ac.html","author":"Hu Yifan","year":"2025","unstructured":"Yifan Hu, Guibin Zhang, Peiyuan Liu, Disen Lan, Naiqi Li, Dawei Cheng, Tao Dai, Shu-Tao Xia, and Shirui Pan. 2025. TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting. In International Conference on Machine Learning (ICML). PMLR. https:\/\/proceedings.mlr.press\/v267\/hu25ac.html"},{"key":"e_1_3_2_2_14_1","volume-title":"SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training. In USENIX Conference on File and Storage Technologies (FAST). USENIX Association, 135-152","author":"Seraj Khan Redwan Ibne","year":"2023","unstructured":"Redwan Ibne Seraj Khan, Ahmad Hossein Yazdani, Yuqi Fu, Arnab K Paul, Bo Ji, Xun Jian, Yue Cheng, and Ali R Butt. 2023. SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training. In USENIX Conference on File and Storage Technologies (FAST). USENIX Association, 135-152. https:\/\/www.usenix.org\/conference\/fast23\/presentation\/khan"},{"key":"e_1_3_2_2_15_1","volume-title":"International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=cGDAkQo1C0p","author":"Kim Taesung","year":"2022","unstructured":"Taesung Kim, Jinhee Kim, Yunwon Tae, Cheonbok Park, Jang-Ho Choi, and Jaegul Choo. 2022. Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=cGDAkQo1C0p"},{"key":"e_1_3_2_2_16_1","unstructured":"Hyunwook Lee and Sungahn Ko. 2024. TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=N0nTk5BSvO"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3357715"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228920"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3224865"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3576647"},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=JePfAI8fah","author":"Liu Yong","year":"2024","unstructured":"Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, and Mingsheng Long. 2024. iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=JePfAI8fah"},{"key":"e_1_3_2_2_23_1","unstructured":"Zhuoran Liu Leqi Zou Xuan Zou Caihua Wang Biao Zhang Da Tang Bolin Zhu Yijie Zhu Peng Wu Ke Wang and Youlong Cheng. 2022. Monolith: Real Time Recommendation System With Collisionless Embedding Table. In Workshop on Online Recommender Systems and User Modeling (ORSUM@RecSys). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-3303\/paper8.pdf"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00090"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3446095.3446100"},{"key":"e_1_3_2_2_26_1","volume-title":"International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=Jbdc0vTOcol","author":"Nie Yuqi","year":"2023","unstructured":"Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2023. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=Jbdc0vTOcol"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/3648160.3648166"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551819"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.10721"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3240567"},{"key":"e_1_3_2_2_31_1","volume-title":"Primus: Unified Training System for Large-Scale Deep Learning Recommendation Models. In USENIX Annual Technical Conference (ATC). USENIX Association, 905-922","author":"Shan Jixi","year":"2025","unstructured":"Jixi Shan, Xiuqi Huang, Yang Guo, Hongyue Mao, Ho-Pang Hsu, Hang Cheng, Can Wang, Jun Song, Rui Shi, Xiaofeng Gao, Jingwei Xu, Shiru Ren, Jiaxiao Zheng, Hua Huang, Lele Yu, Peng Xu, and Guihai Chen. 2025. Primus: Unified Training System for Large-Scale Deep Learning Recommendation Models. In USENIX Annual Technical Conference (ATC). USENIX Association, 905-922. https:\/\/www.usenix.org\/conference\/atc25\/presentation\/shan-jixi"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557702"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527442"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.14778\/3750601.3750620"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707229"},{"key":"e_1_3_2_2_36_1","volume-title":"TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=7oLshfEIC2","author":"Wang Shiyu","year":"2024","unstructured":"Shiyu Wang, Haixu Wu, Xiaoming Shi, Tengge Hu, Huakun Luo, Lintao Ma, James Y. Zhang, and JUN ZHOU. 2024b. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=7oLshfEIC2"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.13278"},{"key":"e_1_3_2_2_38_1","volume-title":"International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=ju_Uqw384Oq","author":"Wu Haixu","year":"2023","unstructured":"Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2023. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=ju_Uqw384Oq"},{"key":"e_1_3_2_2_39_1","first-page":"22419","article-title":"Autoformer","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting. In Advances in Neural Information Processing Systems (NeurIPS). 22419-22430. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/bcc0d400288793e8bdcd7c19a8ac0c2b-Abstract.html","journal-title":"Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00250"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3176753"},{"key":"e_1_3_2_2_44_1","unstructured":"Yunhao Zhang and Junchi Yan. 2023. Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting. In International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/openreview.net\/forum?id=vSVLM2j9eie"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3536313"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567499"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533044"},{"key":"e_1_3_2_2_48_1","volume-title":"Tectonic-Shift: A Composite Storage Fabric for Large-Scale ML Training. In USENIX Annual Technical Conference (ATC). USENIX Association, 433-449","author":"Zhao Mark","year":"2023","unstructured":"Mark Zhao, Satadru Pan, Niket Agarwal, Zhaoduo Wen, David Xu, Anand Natarajan, Pavan Kumar, Shiva Shankar P., Ritesh Tijoriwala, Karan Asher, Hao Wu, Aarti Basant, Daniel Ford, Delia David, Nezih Yigitbasi, Pratap Singh, Carole-Jean Wu, and Christos Kozyrakis. 2023b. Tectonic-Shift: A Composite Storage Fabric for Large-Scale ML Training. In USENIX Annual Technical Conference (ATC). USENIX Association, 433-449. https:\/\/www.usenix.org\/conference\/atc23\/presentation\/zhao"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3325625"},{"key":"e_1_3_2_2_50_1","unstructured":"Martin Zinkevich. 2025. Rules of Machine Learning: Best Practices for ML Engineering. https:\/\/developers.google.com\/machine-learning\/guides\/rules-of-ml A practical engineering guide for building and deploying reliable ML systems."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:24:18Z","timestamp":1786065858000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818410"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":50,"alternative-id":["10.1145\/3770855.3818410","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818410","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}