{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:00:17Z","timestamp":1775595617119,"version":"3.50.1"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"Hong Kong Research Grants Council","award":["12202024 &amp; 12200022"],"award-info":[{"award-number":["12202024 &amp; 12200022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,4,2]]},"abstract":"<jats:p>Indexes are critical for efficient data retrieval and updates in modern databases. Recent advances in machine learning have led to the development of learned indexes, which model the cumulative distribution function of data to predict search positions and accelerate query processing. While learned indexes substantially outperform traditional structures for point lookups, they often suffer from high tail latency, suboptimal range query performance, and inconsistent effectiveness across diverse workloads. To address these challenges, this paper proposes HIRE, a hybrid in-memory index structure designed to deliver efficient performance consistently. HIRE combines the structural and performance robustness of traditional indexes with the predictive power of model-based prediction to reduce search overhead while maintaining worst-case stability. Specifically, it employs (1) hybrid leaf nodes adaptive to varying data distributions and workloads, (2) model-accelerated internal nodes augmented by log-based updates for efficient updates, (3) a non-blocking, cost-driven recalibration mechanism for dynamic data, and (4) an inter-level optimized bulk-loading algorithm accounting for leaf and internal-node errors. Experimental results on multiple real-world datasets demonstrate that HIRE outperforms both state-of-the-art learned indexes and traditional structures in range-query throughput, tail latency, and overall stability. Compared to state-of-the-art learned indexes and traditional indexes, HIRE achieves up to 41.7x higher throughput under mixed workloads, reduces tail latency by up to 98% across varying scenarios.<\/jats:p>","DOI":"10.1145\/3786657","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:54:13Z","timestamp":1775584453000},"page":"1-25","source":"Crossref","is-referenced-by-count":0,"title":["HIRE: A Hybrid Learned Index for Robust and Efficient Performance under Mixed Workloads"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3085-4878","authenticated-orcid":false,"given":"Xinyi","family":"Zhang","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4566-6178","authenticated-orcid":false,"given":"Liang","family":"Liang","sequence":"additional","affiliation":[{"name":"EPFL, Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9949-3639","authenticated-orcid":false,"given":"Anastasia","family":"Ailamaki","sequence":"additional","affiliation":[{"name":"EPFL, Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9404-5848","authenticated-orcid":false,"given":"Jianliang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639302"},{"key":"e_1_2_1_2_1","volume-title":"Evaluating Learned Indexes for External-Memory Joins. arXiv preprint arXiv:2407.00590","author":"Chesetti Yuvaraj","year":"2024","unstructured":"Yuvaraj Chesetti and Prashant Pandey. 2024. Evaluating Learned Indexes for External-Memory Joins. arXiv preprint arXiv:2407.00590 (2024)."},{"key":"e_1_2_1_3_1","volume-title":"Tuning Hierarchical Learned Indexes on Disk and Beyond. In ACM SIGMOD International Conference on Management of Data. 2515-2517","author":"Chockchowwat Supawit","year":"2022","unstructured":"Supawit Chockchowwat. 2022. Tuning Hierarchical Learned Indexes on Disk and Beyond. In ACM SIGMOD International Conference on Management of Data. 2515-2517."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617308"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654919"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/356770.356776"},{"key":"e_1_2_1_7_1","first-page":"9517","volume-title":"When Learned Indexes Meet Persistent Memory: The Analysis and the Optimization. IEEE Trans. Knowl. Data Eng.","volume":"36","author":"Cui Lixiao","year":"2024","unstructured":"Lixiao Cui, Yijing Luo, Yusen Li, Gang Wang, and Xiaoguang Liu. 2024. When Learned Indexes Meet Persistent Memory: The Analysis and the Optimization. IEEE Trans. Knowl. Data Eng., Vol. 36, 12 (2024), 9517-9531."},{"key":"e_1_2_1_8_1","volume-title":"ALEX: An Updatable Adaptive Learned Index. In ACM SIGMOD International Conference on Management of Data. 969-984","author":"Ding Jialin","year":"2020","unstructured":"Jialin Ding, Umar Farooq Minhas, Jia Yu, Chi Wang, Jaeyoung Do, Yinan Li, Hantian Zhang, Badrish Chandramouli, Johannes Gehrke, Donald Kossmann, et al., 2020. ALEX: An Updatable Adaptive Learned Index. In ACM SIGMOD International Conference on Management of Data. 969-984."},{"key":"e_1_2_1_9_1","first-page":"3123","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML","volume":"119","author":"Ferragina Paolo","year":"2020","unstructured":"Paolo Ferragina, Fabrizio Lillo, and Giorgio Vinciguerra. 2020. Why Are Learned Indexes So Effective?. In Proceedings of the 37th International Conference on Machine Learning, ICML, Vol. 119. 3123-3132."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/3389133.3389135"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319860"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626752"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the 24th International Conference on Extending Database Technology, EDBT. 253-264","author":"Hadian Ali","year":"2021","unstructured":"Ali Hadian and Thomas Heinis. 2021. Shift-Table: A Low-latency Learned Index for Range Queries using Model Correction. In Proceedings of the 24th International Conference on Extending Database Technology, EDBT. 253-264."},{"key":"e_1_2_1_14_1","volume-title":"Statistical digital signal processing and modeling","author":"Hayes Monson H","unstructured":"Monson H Hayes. 1996. Statistical digital signal processing and modeling. John Wiley & Sons."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3401071.3401659"},{"key":"e_1_2_1_16_1","volume-title":"The Case for Learned Index Structures. In ACM SIGMOD International Conference on Management of Data. 489-504","author":"Kraska Tim","year":"2018","unstructured":"Tim Kraska, Alex Beutel, Ed H Chi, Jeffrey Dean, and Neoklis Polyzotis. 2018. The Case for Learned Index Structures. In ACM SIGMOD International Conference on Management of Data. 489-504."},{"key":"e_1_2_1_17_1","volume-title":"A Simple Yet High-Performing On-disk Learned Index: Can We Have Our Cake and Eat it Too. arXiv preprint arXiv:2306.02604","author":"Lan Hai","year":"2023","unstructured":"Hai Lan, Zhifeng Bao, J Shane Culpepper, Renata Borovica-Gajic, and Yu Dong. 2023. A Simple Yet High-Performing On-disk Learned Index: Can We Have Our Cake and Eat it Too. arXiv preprint arXiv:2306.02604 (2023)."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00369"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/3489496.3489512"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598593"},{"key":"e_1_2_1_21_1","volume-title":"Luis Alberto Croquevielle, and Thomas Heinis","author":"Liang Liang","year":"2024","unstructured":"Liang Liang, Guang Yang, Ali Hadian, Luis Alberto Croquevielle, and Thomas Heinis. 2024. SWIX: A Memory-efficient Sliding Window Learned Index. Proceedings of the ACM on Management of Data, Vol. 2, 1 (2024), 41:1-41:26."},{"key":"e_1_2_1_22_1","volume-title":"Why Are Learned Indexes So Effective but Sometimes Ineffective? arXiv preprint arXiv:2410.00846","author":"Liu Qiyu","year":"2024","unstructured":"Qiyu Liu, Siyuan Han, Yanlin Qi, Jingshu Peng, Jin Li, Longlong Lin, and Lei Chen. 2024. Why Are Learned Indexes So Effective but Sometimes Ineffective? arXiv preprint arXiv:2410.00846 (2024)."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-024-00893-6"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494141"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421425"},{"key":"e_1_2_1_26_1","volume-title":"AUUG Conference Proceedings","volume":"175","author":"McKenney Paul E","year":"2001","unstructured":"Paul E McKenney, Jonathan Appavoo, Andi Kleen, Orran Krieger, Rusty Russell, Dipankar Sarma, and Maneesh Soni. 2001. Read-copy update. In AUUG Conference Proceedings, Vol. 175."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s002360050048"},{"key":"e_1_2_1_28_1","first-page":"347","volume-title":"Predicate Caching: Query-Driven Secondary Indexing for Cloud Data Warehouses. In Companion of the 2024 International Conference on Management of Data, SIGMOD\/PODS","author":"Schmidt Tobias","year":"2024","unstructured":"Tobias Schmidt, Andreas Kipf, Dominik Horn, Gaurav Saxena, and Tim Kraska. 2024. Predicate Caching: Query-Driven Secondary Indexing for Cloud Data Warehouses. In Companion of the 2024 International Conference on Management of Data, SIGMOD\/PODS 2024. ACM, 347-359."},{"key":"e_1_2_1_29_1","unstructured":"Abraham Silberschatz Henry F Korth and Shashank Sudarshan. 2011. Database system concepts. (2011)."},{"key":"e_1_2_1_30_1","volume-title":"PLEX: Towards Practical Learned Indexing. arXiv preprint arXiv:2108.05117","author":"Stoian Mihail","year":"2021","unstructured":"Mihail Stoian, Andreas Kipf, Ryan Marcus, and Tim Kraska. 2021. PLEX: Towards Practical Learned Indexing. arXiv preprint arXiv:2108.05117 (2021)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3594512.3594528"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374547"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725257"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409963.3410496"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3634915"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551848"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457393"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings 26th International Conference on Extending Database Technology, EDBT. 234-246","author":"Yang Guang","year":"2023","unstructured":"Guang Yang, Liang Liang, Ali Hadian, and Thomas Heinis. 2023. FLIRT: A Fast Learned Index for Rolling Time frames. In Proceedings 26th International Conference on Extending Database Technology, EDBT. 234-246."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682010"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551823"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654954"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673113"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654948"},{"key":"e_1_2_1_44_1","volume-title":"HIRE: A Hybrid Learned Index for Robust and Efficient Performance under Mixed Workloads (Technical Report). https:\/\/arxiv.org\/abs\/2511.21307.","author":"Zhang Xinyi","year":"2025","unstructured":"Xinyi Zhang, Liang Liang, Anastasia Ailamaki, and Jianliang Xu. 2025. HIRE: A Hybrid Learned Index for Robust and Efficient Performance under Mixed Workloads (Technical Report). https:\/\/arxiv.org\/abs\/2511.21307."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW55742.2022.00024"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:59:54Z","timestamp":1775591994000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,4,2]]}},"alternative-id":["10.1145\/3786657"],"URL":"https:\/\/doi.org\/10.1145\/3786657","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]}}}