{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:20:21Z","timestamp":1768569621919,"version":"3.49.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFB4505201"],"award-info":[{"award-number":["2024YFB4505201"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tc.2025.3625161","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:40:26Z","timestamp":1763404826000},"page":"448-461","source":"Crossref","is-referenced-by-count":0,"title":["FIITED: Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4427-396X","authenticated-orcid":false,"given":"Qinyi","family":"Luo","sequence":"first","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9308-6273","authenticated-orcid":false,"given":"Penghan","family":"Wang","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9405-447X","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0472-107X","authenticated-orcid":false,"given":"Fan","family":"Lai","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Jiachen","family":"Mao","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Xiaohan","family":"Wei","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Jun","family":"Song","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7259-3691","authenticated-orcid":false,"given":"Wei-Yu","family":"Tsai","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Yuxi","family":"Hu","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3950-1264","authenticated-orcid":false,"given":"Xuehai","family":"Qian","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Understanding scaling laws for recommendation models","author":"Ardalani","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467220"},{"key":"ref3","first-page":"762","article-title":"Random offset block embedding (robe) for compressed embedding tables in deep learning recommendation systems","volume-title":"Proc. Mach. Learn. Syst.","volume":"4","author":"Desai","year":"2022"},{"key":"ref4","first-page":"40","article-title":"Bandana: Using non-volatile memory for storing deep learning models","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Eisenman","year":"2019"},{"key":"ref5","article-title":"A frequency-aware software cache for large recommendation system embeddings","author":"Fang","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00095"},{"key":"ref7","article-title":"Training with multi-layer embeddings for model reduction","author":"Ghaemmaghami","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9517710"},{"key":"ref9","first-page":"364","article-title":"Adaptive sampling for SGD by exploiting side information","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Gopal","year":"2016"},{"key":"ref10","article-title":"Post-training 4-bit quantization on embedding tables","author":"Guan","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589112"},{"key":"ref13","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Jia","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403288"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00059"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3186387"},{"key":"ref17","first-page":"817","article-title":"AdaEmbed: Adaptive embedding for Large-Scale recommendation models","volume-title":"Proc. 17th USENIX Symp. Oper. Syst. Des. Implementation (OSDI),","author":"Lai","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446717"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539070"},{"key":"ref20","article-title":"Anchor & transform: Learning sparse embeddings for large vocabularies","author":"Liang","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401436"},{"key":"ref22","article-title":"Learnable embedding sizes for recommender systems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2021"},{"key":"ref23","first-page":"266","article-title":"Disaggregated multi-tower: Topology-aware modeling technique for efficient large scale recommendation","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Luo","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14778\/3489496.3489511"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref26","article-title":"Deep learning recommendation model for personalization and recommendation systems","author":"Naumov","year":"2019"},{"key":"ref27","first-page":"382","article-title":"Learning compressed embeddings for on-device inference","volume-title":"Proc. Mach. Learn. Syst.","volume":"4","author":"Pansare","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401440"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532060"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507777"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547405"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640406"},{"key":"ref35","first-page":"667","article-title":"$\\{${OPER$\\}$}:$\\{${Optimality-Guided$\\}$} embedding table parallelization for large-scale recommendation model","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC),","author":"Wang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482130"},{"key":"ref37","article-title":"Mixed-precision embedding using a cache","author":"Yang","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582029"},{"key":"ref39","first-page":"1141","article-title":"Accelerating neural recommendation training with embedding scheduling","volume-title":"Proc. 21st USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Zeng","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412227"},{"key":"ref41","first-page":"412","article-title":"Distributed hierarchical GPU parameter server for massive scale deep learning ads systems","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Zhao","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450124"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"ref45","first-page":"526","article-title":"On optimizing the communication of model parallelism","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Zhuang","year":"2023"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11353113\/11251069.pdf?arnumber=11251069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:49:33Z","timestamp":1768510173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11251069\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":45,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3625161","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}