{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:24:55Z","timestamp":1787689495933,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780212","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2066-2075","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hitcher: Efficient GPU-based Vector Search via Cluster-Centric Kernel and Hitch-Ride Ordering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8927-3325","authenticated-orcid":false,"given":"Qihui","family":"Zhou","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2768-1224","authenticated-orcid":false,"given":"Changji","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9837-0904","authenticated-orcid":false,"given":"Guanxian","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3243-8512","authenticated-orcid":false,"given":"Chenhao","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2122-915X","authenticated-orcid":false,"given":"Xiao","family":"Yan","sequence":"additional","affiliation":[{"name":"Institute for Math and AI, Wuhan, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9803-4927","authenticated-orcid":false,"given":"Yu","family":"Mao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4029-757X","authenticated-orcid":false,"given":"Ming-Chang","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-6288","authenticated-orcid":false,"given":"James","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2017. Unified Memory for CUDA. https:\/\/developer.nvidia.com\/blog\/unified-memory-cuda-beginners\/"},{"key":"e_1_3_2_2_2_1","unstructured":"2025. Hnswlib - fast approximate nearest neighbor searc. https:\/\/github.com\/nmslib\/hnswlib"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611537"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-TUTORIALS.6"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.IS.2019.02.006"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248038"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-01258--8_13"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-01258--8_13"},{"key":"e_1_3_2_2_9_1","volume-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216","author":"Chen Jianlv","year":"2024","unstructured":"Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)."},{"key":"e_1_3_2_2_10_1","volume-title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Chen Qi","year":"2021","unstructured":"Qi Chen, Bing Zhao, Haidong Wang, Mingqin Li, Chuanjie Liu, Zengzhong Li, Mao Yang, and Jingdong Wang. 2021. SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 5199--5212. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/299dc35e747eb77177d9cea10a802da2-Abstract.html"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242610"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrqa-1.1"},{"key":"e_1_3_2_2_13_1","volume-title":"Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search. arXiv preprint arXiv:2411.17229","author":"Deng Liwei","year":"2024","unstructured":"Liwei Deng, Penghao Chen, Ximu Zeng, Tianfu Wang, Yan Zhao, and Kai Zheng. 2024. Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search. arXiv preprint arXiv:2411.17229 (2024)."},{"key":"e_1_3_2_2_14_1","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arXiv:2401.08281 [cs.LG]"},{"key":"e_1_3_2_2_15_1","unstructured":"Wikimedia Foundation. 2007. Wikimedia Downloads. https:\/\/dumps.wikimedia.org"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_3_2_2_18_1","volume-title":"Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search. arXiv preprint arXiv:2409.09913","author":"Gao Jianyang","year":"2024","unstructured":"Jianyang Gao, Yutong Gou, Yuexuan Xu, Yongyi Yang, Cheng Long, and Raymond Chi-Wing Wong. 2024. Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search. arXiv preprint arXiv:2409.09913 (2024)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589282"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654970"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.379"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219885"},{"key":"e_1_3_2_2_23_1","volume-title":"REALM: Retrieval-Augmented Language Model Pre-Training. In ICML. https:\/\/arxiv.org\/abs\/2002.08909","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. REALM: Retrieval-Augmented Language Model Pre-Training. In ICML. https:\/\/arxiv.org\/abs\/2002.08909"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_2_27_1","volume-title":"Ravishankar Krishnawamy, and Rohan Kadekodi.","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, and Rohan Kadekodi. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. Advances in neural information processing Systems 32 (2019)."},{"key":"e_1_3_2_2_28_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","unstructured":"Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence 33, 1 (2010), 117--128."},{"key":"e_1_3_2_2_29_1","volume-title":"Piperag: Fast retrieval-augmented generation via algorithm-system co-design. arXiv preprint arXiv:2403.05676","author":"Jiang Wenqi","year":"2024","unstructured":"Wenqi Jiang, Shuai Zhang, Boran Han, Jie Wang, Bernie Wang, and Tim Kraska. 2024. Piperag: Fast retrieval-augmented generation via algorithm-system co-design. arXiv preprint arXiv:2403.05676 (2024)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and effective passage search via contextualized late interaction over BERT. In SIGIR. https:\/\/arxiv.org\/abs\/2004.12832","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467101"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01454"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_2_37_1","volume-title":"Bing Chat surpasses 1 billion daily queries. https:\/\/blogs.microsoft.com\/. Accessed","year":"2025","unstructured":"Microsoft. 2023. Bing Chat surpasses 1 billion daily queries. https:\/\/blogs.microsoft.com\/. Accessed May 2025."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00323"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577527"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1162\/TACL_A_00605"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.16576"},{"key":"e_1_3_2_2_44_1","volume-title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. arXiv preprint arXiv:1908.08962v2","author":"Turc Iulia","year":"2019","unstructured":"Iulia Turc, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. arXiv preprint arXiv:1908.08962v2 (2019)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.11324"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639269"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11227-019-03079-Y"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331198"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539212"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219820"},{"key":"e_1_3_2_2_52_1","volume-title":"Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024","author":"Zhang Zili","year":"2024","unstructured":"Zili Zhang, Fangyue Liu, Gang Huang, Xuanzhe Liu, and Xin Jin. 2024. Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024, Santa Clara, CA, April 15--17, 2024, Laurent Vanbever and Irene Zhang (Eds.). USENIX Association, 23--40. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/zhang-zili-pipelining"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00094"}],"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.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:07:44Z","timestamp":1787688464000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":53,"alternative-id":["10.1145\/3770854.3780212","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780212","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}