{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:58:15Z","timestamp":1775815095115,"version":"3.50.1"},"reference-count":82,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:00:00Z","timestamp":1705017600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376103, 62302184, and 62206102"],"award-info":[{"award-number":["62376103, 62302184, and 62206102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100005064","name":"Science and Technology Support Program of Hubei Province","doi-asserted-by":"crossref","award":["2022BAA046"],"award-info":[{"award-number":["2022BAA046"]}],"id":[{"id":"10.13039\/501100005064","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"<jats:p>To alleviate the problem of information explosion, recommender systems are widely deployed to provide personalized information filtering services. Usually, embedding tables are employed in recommender systems to transform high-dimensional sparse one-hot vectors into dense real-valued embeddings. However, the embedding tables are huge and account for most of the parameters in industrial-scale recommender systems. In order to reduce memory costs and improve efficiency, various approaches are proposed to compress the embedding tables. In this survey, we provide a comprehensive review of embedding compression approaches in recommender systems. We first introduce deep learning recommendation models and the basic concept of embedding compression in recommender systems. Subsequently, we systematically organize existing approaches into three categories: low precision, mixed dimension, and weight sharing. Lastly, we summarize the survey with some general suggestions and provide future prospects for this field.<\/jats:p>","DOI":"10.1145\/3637841","type":"journal-article","created":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T11:26:58Z","timestamp":1702639618000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Embedding Compression in Recommender Systems: A Survey"],"prefix":"10.1145","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7067-0275","authenticated-orcid":false,"given":"Shiwei","family":"Li","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7393-8994","authenticated-orcid":false,"given":"Huifeng","family":"Guo","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4360-0754","authenticated-orcid":false,"given":"Xing","family":"Tang","sequence":"additional","affiliation":[{"name":"Tencent, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7791-5511","authenticated-orcid":false,"given":"Ruiming","family":"Tang","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4694-1821","authenticated-orcid":false,"given":"Lu","family":"Hou","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9224-2431","authenticated-orcid":false,"given":"Ruixuan","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8132-6250","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"ruizhang.info, China"}]}],"member":"320","published-online":{"date-parts":[[2024,1,12]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.124"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467220"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1022"},{"key":"e_1_3_2_6_2","article-title":"Towards low-loss 1-bit quantization of user-item representations for top-K recommendation","volume":"2112","author":"Chen Yankai","year":"2021","unstructured":"Yankai Chen, Yifei Zhang, Yingxue Zhang, Huifeng Guo, Jingjie Li, Ruiming Tang, Xiuqiang He, and Irwin King. 2021. Towards low-loss 1-bit quantization of user-item representations for top-K recommendation. CoRR abs\/2112.01944 (2021).","journal-title":"CoRR"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_8_2","article-title":"Differentiable neural input search for recommender systems","volume":"2006","author":"Cheng Weiyu","year":"2020","unstructured":"Weiyu Cheng, Yanyan Shen, and Linpeng Huang. 2020. Differentiable neural input search for recommender systems. CoRR abs\/2006.04466 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"e_1_3_2_10_2","first-page":"3123","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. BinaryConnect: Training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada. 3123\u20133131."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441727"},{"key":"e_1_3_2_12_2","first-page":"762","article-title":"Random offset block embedding (ROBE) for compressed embedding tables in deep learning recommendation systems","volume":"4","author":"Desai Aditya","year":"2022","unstructured":"Aditya Desai, Li Chou, and Anshumali Shrivastava. 2022. Random offset block embedding (ROBE) for compressed embedding tables in deep learning recommendation systems. Proceedings of Machine Learning and Systems 4 (2022), 762\u2013778.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_13_2","article-title":"Semantically constrained memory allocation (SCMA) for embedding in efficient recommendation systems","volume":"2103","author":"Desai Aditya","year":"2021","unstructured":"Aditya Desai, Yanzhou Pan, Kuangyuan Sun, et\u00a0al. 2021. Semantically constrained memory allocation (SCMA) for embedding in efficient recommendation systems. CoRR abs\/2103.06124 (2021).","journal-title":"CoRR"},{"key":"e_1_3_2_14_2","volume-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","author":"Esser Steven K.","year":"2020","unstructured":"Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S. Modha. 2020. Learned step size quantization. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net."},{"key":"e_1_3_2_15_2","article-title":"Training with multi-layer embeddings for model reduction","volume":"2006","author":"Ghaemmaghami Benjamin","year":"2020","unstructured":"Benjamin Ghaemmaghami, Zihao Deng, Benjamin Y. Cho, et\u00a0al. 2020. Training with multi-layer embeddings for model reduction. CoRR abs\/2006.05623 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_16_2","first-page":"2786","volume-title":"IEEE International Symposium on Information Theory, ISIT 2021, Melbourne, Australia, July 12\u201320, 2021","author":"Ginart Antonio A.","year":"2021","unstructured":"Antonio A. Ginart, Maxim Naumov, Dheevatsa Mudigere, Jiyan Yang, and James Zou. 2021. Mixed dimension embeddings with application to memory-efficient recommendation systems. In IEEE International Symposium on Information Theory, ISIT 2021, Melbourne, Australia, July 12\u201320, 2021. IEEE, 2786\u20132791."},{"key":"e_1_3_2_17_2","article-title":"Post-training 4-bit quantization on embedding tables","volume":"1911","author":"Guan Hui","year":"2019","unstructured":"Hui Guan, Andrey Malevich, Jiyan Yang, Jongsoo Park, and Hector Yuen. 2019. Post-training 4-bit quantization on embedding tables. CoRR abs\/1911.02079 (2019).","journal-title":"CoRR"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462976"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3487045"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"e_1_3_2_23_2","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparameterization with Gumbel-Softmax. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462941"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403288"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366424.3383416"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467304"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357930"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411912"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462878"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25564"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.69"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098008"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380151"},{"key":"e_1_3_2_36_2","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Liang Paul Pu","year":"2021","unstructured":"Paul Pu Liang, Manzil Zaheer, Yuan Wang, and Amr Ahmed. 2021. Anchor & transform: Learning sparse embeddings for large vocabularies. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313497"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/479"},{"key":"e_1_3_2_39_2","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019","author":"Liu Hanxiao","year":"2019","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2019. DARTS: Differentiable architecture search. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019. OpenReview.net."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401436"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806603"},{"key":"e_1_3_2_42_2","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","author":"Liu Siyi","year":"2021","unstructured":"Siyi Liu, Chen Gao, Yihong Chen, Depeng Jin, and Yong Li. 2021. Learnable embedding sizes for recommender systems. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021. OpenReview.net."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.275"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557411"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210104"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482297"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_48_2","volume-title":"Proceedings of Machine Learning and Systems 2022, MLSys 2022, Santa Clara, CA, USA, August 29\u2013September 1, 2022","author":"Pansare Niketan","year":"2022","unstructured":"Niketan Pansare, Jay Katukuri, Aditya Arora, Frank Cipollone, Riyaaz Shaik, Noyan Tokgozoglu, and Chandru Venkataraman. 2022. Learning compressed embeddings for on-device inference. In Proceedings of Machine Learning and Systems 2022, MLSys 2022, Santa Clara, CA, USA, August 29\u2013September 1, 2022. mlsys.org."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532060"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403059"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16561"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539238"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401125"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380266"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611967"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380170"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482234"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553516"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3145690"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3409963.3410498"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449946"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531775"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/435"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457236"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482065"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482130"},{"key":"e_1_3_2_70_2","article-title":"Mixed-precision embedding using a cache","volume":"2010","author":"Yang Jie Amy","year":"2020","unstructured":"Jie Amy Yang, Jianyu Huang, Jongsoo Park, Ping Tak Peter Tang, and Andrew Tulloch. 2020. Mixed-precision embedding using a cache. CoRR abs\/2010.11305 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380237"},{"key":"e_1_3_2_72_2","volume-title":"Proceedings of Machine Learning and Systems 2021, MLSys 2021, Virtual Event, April 5\u20139, 2021","author":"Yin Chunxing","year":"2021","unstructured":"Chunxing Yin, Bilge Acun, Carole-Jean Wu, and Xing Liu. 2021. TT-Rec: Tensor train compression for deep learning recommendation models. In Proceedings of Machine Learning and Systems 2021, MLSys 2021, Virtual Event, April 5\u20139, 2021. mlsys.org."},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412227"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911502"},{"issue":"1","key":"e_1_3_2_75_2","first-page":"5:1\u20135:38","article-title":"Deep learning based recommender system: A survey and new perspectives","volume":"52","author":"Zhang Shuai","year":"2019","unstructured":"Shuai Zhang, Lina Yao, Aixin Sun, and Yi Tay. 2019. Deep learning based recommender system: A survey and new perspectives. ACM Comput. Surv. 52, 1 (2019), 5:1\u20135:38.","journal-title":"ACM Comput. Surv."},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/636"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10764"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609578"},{"key":"e_1_3_2_79_2","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Haochen Liu Wenqi Fan Hui Liu Jiliang Tang Chong Wang Ming Chen Xudong Zheng Xiaobing Liu and Xiwang Yang. 2021. AutoEmb: Automated embedding dimensionality search in streaming recommendations. (2021) 896\u2013905.","DOI":"10.1109\/ICDM51629.2021.00101"},{"key":"e_1_3_2_80_2","article-title":"Memory-efficient embedding for recommendations","volume":"2006","author":"Zhao Xiangyu","year":"2020","unstructured":"Xiangyu Zhao, Haochen Liu, Hui Liu, Jiliang Tang, Weiwei Guo, Jun Shi, Sida Wang, Huiji Gao, and Bo Long. 2020. Memory-efficient embedding for recommendations. CoRR abs\/2006.14827 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531723"},{"key":"e_1_3_2_83_2","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc V. Le. 2017. Neural architecture search with reinforcement learning. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net."}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637841","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:18Z","timestamp":1750286958000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,12]]},"references-count":82,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3637841"],"URL":"https:\/\/doi.org\/10.1145\/3637841","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,12]]},"assertion":[{"value":"2022-10-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}