{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T20:02:59Z","timestamp":1779825779003,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":61,"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":["62402187"],"award-info":[{"award-number":["62402187"]}]},{"name":"National Natural Science Foundation of China","award":["U22A2027"],"award-info":[{"award-number":["U22A2027"]}]},{"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":[[2026,5,31]]},"DOI":"10.1145\/3788853.3803078","type":"proceedings-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:14:47Z","timestamp":1779822887000},"page":"293-306","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TokaDB: A Unified Storage Engine for Training-Serving Data Management in Large Recommendation Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4741-9282","authenticated-orcid":false,"given":"Peng","family":"Fang","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7758-3819","authenticated-orcid":false,"given":"Kelei","family":"Guo","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2622-4075","authenticated-orcid":false,"given":"Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6192-6612","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4915-354X","authenticated-orcid":false,"given":"Mingming","family":"Chen","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8598-4051","authenticated-orcid":false,"given":"Huaye","family":"Xu","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7263-5158","authenticated-orcid":false,"given":"Borong","family":"Meng","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0762-0888","authenticated-orcid":false,"given":"Zongjia","family":"Chen","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3686-0789","authenticated-orcid":false,"given":"Mingshuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4345-9035","authenticated-orcid":false,"given":"Luping","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4877-473X","authenticated-orcid":false,"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2430-2009","authenticated-orcid":false,"given":"Shiru","family":"Ren","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2791-4158","authenticated-orcid":false,"given":"Fang","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4674-6006","authenticated-orcid":false,"given":"Dan","family":"Feng","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687625"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376712"},{"key":"e_1_3_2_1_3_1","unstructured":"Apache Iceberg. [n.d.]. Apache Iceberg: The Open Table Format for Analytic Datasets. https:\/\/iceberg.apache.org\/. Accessed: 2025-11-15."},{"key":"e_1_3_2_1_4_1","volume-title":"Apache Doris: High-performance real-time analytical database. https:\/\/doris.apache.org\/. Accessed: 2025-10-30.","author":"Foundation Apache Software","year":"2023","unstructured":"Apache Software Foundation. 2023. Apache Doris: High-performance real-time analytical database. https:\/\/doris.apache.org\/. Accessed: 2025-10-30."},{"key":"e_1_3_2_1_5_1","volume-title":"Understanding scaling laws for recommendation models. arXiv preprint arXiv:2208.08489","author":"Ardalani Newsha","year":"2022","unstructured":"Newsha Ardalani, Carole-Jean Wu, Zeliang Chen, Bhargav Bhushanam, and Adnan Aziz. 2022. Understanding scaling laws for recommendation models. arXiv preprint arXiv:2208.08489 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915231"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2758"},{"key":"e_1_3_2_1_8_1","unstructured":"ByteDance. 2025. TerarkDB. Available online. https:\/\/github.com\/bytedance\/terarkdb"},{"key":"e_1_3_2_1_9_1","unstructured":"ByteDance. 2025. VolcanoEngine. Available online. https:\/\/www.volcengine.com"},{"key":"e_1_3_2_1_10_1","volume-title":"The Bulletin of the Technical Committee on Data Engineering","volume":"38","author":"Carbone Paris","year":"2015","unstructured":"Paris Carbone, Asterios Katsifodimos, Stephan Ewen, Volker Markl, Seif Haridi, and Kostas Tzoumas. 2015. Apache flink: Stream and batch processing in a single engine. The Bulletin of the Technical Committee on Data Engineering, Vol. 38, 4 (2015)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3748065"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599922"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et al. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology Vol. 15 3 (2024) 1-45.","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_14_1","volume-title":"Hllm: Enhancing sequential recommendations via hierarchical large language models for item and user modeling. arXiv preprint arXiv:2409.12740","author":"Chen Junyi","year":"2024","unstructured":"Junyi Chen, Lu Chi, Bingyue Peng, and Zehuan Yuan. 2024. Hllm: Enhancing sequential recommendations via hierarchical large language models for item and user modeling. arXiv preprint arXiv:2409.12740 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611545"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_17_1","volume-title":"M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084","author":"Cui Zeyu","year":"2022","unstructured":"Zeyu Cui, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3661821"},{"key":"e_1_3_2_1_19_1","volume-title":"Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment. arXiv preprint arXiv:2502.18965","author":"Deng Jiaxin","year":"2025","unstructured":"Jiaxin Deng, Shiyao Wang, Kuo Cai, Lejian Ren, Qigen Hu, Weifeng Ding, Qiang Luo, and Guorui Zhou. 2025. Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment. arXiv preprint arXiv:2502.18965 (2025)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/363095.363141"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3483840"},{"key":"e_1_3_2_1_22_1","volume-title":"http:\/\/rocksdb.org\/. Accessed","author":"DB.","year":"2021","unstructured":"Facebook. 2018. BlobDB. http:\/\/rocksdb.org\/. Accessed: October 3, 2021."},{"key":"e_1_3_2_1_23_1","volume-title":"Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines. arXiv preprint arXiv:2510.11317","author":"Gao Chen","year":"2025","unstructured":"Chen Gao, Zixin Zhao, Lv Shao, and Tong Liu. 2025. Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines. arXiv preprint arXiv:2510.11317 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"A survey on user behavior modeling in recommender systems. arXiv preprint arXiv:2302.11087","author":"He Zhicheng","year":"2023","unstructured":"Zhicheng He, Weiwen Liu, Wei Guo, Jiarui Qin, Yingxue Zhang, Yaochen Hu, and Ruiming Tang. 2023. A survey on user behavior modeling in recommender systems. arXiv preprint arXiv:2302.11087 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3632093.3632117"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33291"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3748045"},{"key":"e_1_3_2_1_29_1","volume-title":"Cassandra: a decentralized structured storage system. ACM SIGOPS operating systems review","author":"Lakshman Avinash","year":"2010","unstructured":"Avinash Lakshman and Prashant Malik. 2010. Cassandra: a decentralized structured storage system. ACM SIGOPS operating systems review, Vol. 44, 2 (2010), 35-40."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730042"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00036"},{"key":"e_1_3_2_1_32_1","first-page":"1162","volume-title":"Large Memory Network for Recommendation. In Companion Proceedings of the ACM on Web Conference","author":"Lu Hui","year":"2025","unstructured":"Hui Lu, Zheng Chai, Yuchao Zheng, Zhe Chen, Deping Xie, F Peng Xu, Xun Zhou, and Di Wu. 2025. Large Memory Network for Recommendation. In Companion Proceedings of the ACM on Web Conference 2025. 1162-1166."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3033273"},{"key":"e_1_3_2_1_34_1","first-page":"49","volume-title":"21st USENIX Conference on File and Storage Technologies (FAST 23)","author":"Lu Ruiming","year":"2023","unstructured":"Ruiming Lu, Erci Xu, Yiming Zhang, Fengyi Zhu, Zhaosheng Zhu, Mengtian Wang, Zongpeng Zhu, Guangtao Xue, Jiwu Shu, Minglu Li, et al., 2023. Perseus: A detection framework for cloud storage systems. In 21st USENIX Conference on File and Storage Technologies (FAST 23). 49-64."},{"key":"e_1_3_2_1_35_1","volume-title":"MARM: Unlocking the Future of Recommendation Systems through Memory Augmentation and Scalable Complexity. arXiv preprint arXiv:2411.09425","author":"Lv Xiao","year":"2024","unstructured":"Xiao Lv, Jiangxia Cao, Shijie Guan, Xiaoyou Zhou, Zhiguang Qi, Yaqiang Zang, Ming Li, Ben Wang, Kun Gai, and Guorui Zhou. 2024. MARM: Unlocking the Future of Recommendation Systems through Memory Augmentation and Scalable Complexity. arXiv preprint arXiv:2411.09425 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.92.0078"},{"key":"e_1_3_2_1_37_1","volume-title":"The log-structured merge-tree (LSM-tree). Acta informatica","author":"O'Neil Patrick","year":"1996","unstructured":"Patrick O'Neil, Edward Cheng, Dieter Gawlick, and Elizabeth O'Neil. 1996. The log-structured merge-tree (LSM-tree). Acta informatica, Vol. 33, 4 (1996), 351-385."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_39_1","first-page":"606","article-title":"Efficiently scaling transformer inference","volume":"5","author":"Pope Reiner","year":"2023","unstructured":"Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean. 2023. Efficiently scaling transformer inference. Proceedings of machine learning and systems, Vol. 5 (2023), 606-624.","journal-title":"Proceedings of machine learning and systems"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685802"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679922"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/3750601.3750620"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3226595.3226638"},{"key":"e_1_3_2_1_44_1","volume-title":"GRank: Towards Target-Aware and Streamlined Industrial Retrieval with a Generate-Rank Framework. arXiv preprint arXiv:2510.15299","author":"Sun Yijia","year":"2025","unstructured":"Yijia Sun, Shanshan Huang, Zhiyuan Guan, Qiang Luo, Ruiming Tang, Kun Gai, and Guorui Zhou. 2025. GRank: Towards Target-Aware and Streamlined Industrial Retrieval with a Generate-Rank Framework. arXiv preprint arXiv:2510.15299 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2199-0_8"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSNT.2011.6182030"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01291-2"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688104"},{"key":"e_1_3_2_1_50_1","volume-title":"Continual Low-Rank Adapters for LLM-based Generative Recommender Systems. arXiv preprint arXiv:2510.25093","author":"Yoo Hyunsik","year":"2025","unstructured":"Hyunsik Yoo, Ting-Wei Li, SeongKu Kang, Zhining Liu, Charlie Xu, Qilin Qi, and Hanghang Tong. 2025. Continual Low-Rank Adapters for LLM-based Generative Recommender Systems. arXiv preprint arXiv:2510.25093 (2025)."},{"key":"e_1_3_2_1_51_1","volume-title":"2nd USENIX workshop on hot topics in cloud computing (HotCloud 10)","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster computing with working sets. In 2nd USENIX workshop on hot topics in cloud computing (HotCloud 10)."},{"key":"e_1_3_2_1_52_1","unstructured":"Jiaqi Zhai Lucy Liao Xing Liu Yueming Wang Rui Li Xuan Cao Leon Gao Zhaojie Gong Fangda Gu Michael He et al. 2024. Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations. arXiv preprint arXiv:2402.17152 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Wukong: Towards a scaling law for large-scale recommendation. arXiv preprint arXiv:2403.02545","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Daifeng Guo, Yanli Zhao, Shen Li, Yuchen Hao, Yantao Yao, et al., 2024b. Wukong: Towards a scaling law for large-scale recommendation. arXiv preprint arXiv:2403.02545 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688129"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00312"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"e_1_3_2_1_57_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023b. A survey of large language models. arXiv preprint arXiv:2303.18223 Vol. 1 2 (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_1_59_1","volume-title":"Breaking the curse of quality saturation with user-centric ranking. arXiv preprint arXiv:2305.15333","author":"Zhao Zhuokai","year":"2023","unstructured":"Zhuokai Zhao, Yang Yang, Wenyu Wang, Chihuang Liu, Yu Shi, Wenjie Hu, Haotian Zhang, and Shuang Yang. 2023a. Breaking the curse of quality saturation with user-centric ranking. arXiv preprint arXiv:2305.15333 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML. In Companion of the 2025 International Conference on Management of Data. 729-742","author":"Zhou Xuanhe","year":"2025","unstructured":"Xuanhe Zhou, Wei Zhou, Liguo Qi, Hao Zhang, Dihao Chen, Bingsheng He, Mian Lu, Guoliang Li, Fan Wu, and Yuqiang Chen. 2025. OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML. In Companion of the 2025 International Conference on Management of Data. 729-742."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657816"}],"event":{"name":"SIGMOD\/PODS '26: International Conference on Management of Data","location":"Bengaluru India","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Companion of the International Conference on Management of Data"],"original-title":[],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:18:58Z","timestamp":1779823138000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788853.3803078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,30]]},"references-count":61,"alternative-id":["10.1145\/3788853.3803078","10.1145\/3788853"],"URL":"https:\/\/doi.org\/10.1145\/3788853.3803078","relation":{},"subject":[],"published":{"date-parts":[[2026,5,30]]},"assertion":[{"value":"2026-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}