{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:32:08Z","timestamp":1765506728774,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761421","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:52:37Z","timestamp":1762563157000},"page":"2707-2717","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["InstANNS: Scalable Approximate Nearest Neighbor Search via Cost-Efficient In-Storage Processing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0882-407X","authenticated-orcid":false,"given":"Bonggeun","family":"Sim","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5244-5866","authenticated-orcid":false,"given":"Yushin","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3487-5253","authenticated-orcid":false,"given":"Minseo","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1425-0971","authenticated-orcid":false,"given":"Yeonhong","family":"Park","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4266-4919","authenticated-orcid":false,"given":"Jae W.","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2010. Datasets for approximate nearest neighbor search. http:\/\/corpus-texmex.irisa.fr\/."},{"key":"e_1_3_2_1_2_1","unstructured":"2016. ARM developer documentation Tightly Coupled Memory (TCM). https:\/\/developer.arm.com\/documentation\/107565\/0101\/Memorysystem\/Tightly-Coupled-Memory--TCM- Accessed: 2025-05."},{"key":"e_1_3_2_1_3_1","unstructured":"2021. Spacev1b: A billion-scale vector dataset for text descriptors. https:\/\/github. com\/microsoft\/SPTAG\/tree\/master\/datasets\/SPACEV1B"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/3204028.3204034"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-01258--8_13"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749735"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21)","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 neighbor search. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21). Curran Associates Inc., Red Hook, NY, USA, Article 398, 14 pages."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465003"},{"key":"e_1_3_2_1_9_1","volume-title":"Common Crawl: Open Repository of Web Crawl Data. https:\/\/commoncrawl.org\/. Accessed: 2025-05--22.","author":"Crawl Common","year":"2025","unstructured":"Common Crawl. 2025. Common Crawl: Open Repository of Web Crawl Data. https:\/\/commoncrawl.org\/. Accessed: 2025-05--22."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","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]","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"e_1_3_2_1_11_1","volume-title":"EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph. arXiv:1609.07228 [cs.CV] https:\/\/arxiv.org\/abs\/1609.07228","author":"Fu Cong","year":"2016","unstructured":"Cong Fu and Deng Cai. 2016. EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph. arXiv:1609.07228 [cs.CV] https:\/\/arxiv.org\/abs\/1609.07228"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2014.6855544"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589282"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.240"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/645925.671516"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.616"},{"key":"e_1_3_2_1_18_1","unstructured":"Taiga Ikeda Daisuke Miyashita and Jun Deguchi. 2025. On Storage Neural Network Augmented Approximate Nearest Neighbor Search. arXiv:2501.16375 [cs.LG] https:\/\/arxiv.org\/abs\/2501.16375"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717478"},{"key":"e_1_3_2_1_20_1","volume-title":"22nd USENIX Conference on File and Storage Technologies (FAST 24)","author":"Jun Yuhun","year":"2024","unstructured":"Yuhun Jun, Shinhyun Park, Jeong-Uk Kang, Sang-Hoon Kim, and Euiseong Seo. 2024. We Ain't Afraid of No File Fragmentation: Causes and Prevention of Its Performance Impact on Modern Flash SSDs. In 22nd USENIX Conference on File and Storage Technologies (FAST 24). USENIX Association, Santa Clara, CA, 193--208. https:\/\/www.usenix.org\/conference\/fast24\/presentation\/jun"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.298"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.22214\/ijraset.2024.59852"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2007.01.010"},{"key":"e_1_3_2_1_25_1","volume-title":"NVMeVirt: A Versatile Software-defined Virtual NVMe Device. In 21st USENIX Conference on File and Storage Technologies (FAST 23)","author":"Kim Sang-Hoon","year":"2023","unstructured":"Sang-Hoon Kim, Jaehoon Shim, Euidong Lee, Seongyeop Jeong, Ilkueon Kang, and Jin-Soo Kim. 2023. NVMeVirt: A Versatile Software-defined Virtual NVMe Device. In 21st USENIX Conference on File and Storage Technologies (FAST 23). USENIX Association, Santa Clara, CA, 379--394. https:\/\/www.usenix.org\/conference\/ fast23\/presentation\/kim-sang-hoon"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358320"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2013.10.006"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_29_1","volume-title":"Lin (Eds.)","volume":"33","author":"Ren Jie","year":"2020","unstructured":"Jie Ren, Minjia Zhang, and Dong Li. 2020. HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 10672--10684. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/788d986905533aba051261497ecffcbb-Paper.pdf"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: an open large-scale dataset for training next generation image-text models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 1833, 17 pages."},{"volume-title":"DiskANN: fast accurate billionpoint nearest neighbor search on a single node","author":"Subramanya Suhas Jayaram","key":"e_1_3_2_1_31_1","unstructured":"Suhas Jayaram Subramanya, Devvrit, Rohan Kadekodi, Ravishankar Krishaswamy, and Harsha Vardhan Simhadri. 2019. DiskANN: fast accurate billionpoint nearest neighbor search on a single node. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_32_1","volume-title":"Scalable Billion-point Approximate Nearest Neighbor Search Using SmartSSDs. In 2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Tian Bing","year":"2024","unstructured":"Bing Tian, Haikun Liu, Zhuohui Duan, Xiaofei Liao, Hai Jin, and Yu Zhang. 2024. Scalable Billion-point Approximate Nearest Neighbor Search Using SmartSSDs. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 1135--1150. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/tian"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3724648.3724659"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639269"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476255"},{"key":"e_1_3_2_1_37_1","volume-title":"Bell","author":"Witten Ian H.","year":"1999","unstructured":"Ian H. Witten, Alistair Moffat, and Timothy C. Bell. 1999. Managing gigabytes (2nd ed.): compressing and indexing documents and images. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.","edition":"2"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.226"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2017.14"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357938"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/296854.277632"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:28:16Z","timestamp":1765506496000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":41,"alternative-id":["10.1145\/3746252.3761421","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761421","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}