{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:53:22Z","timestamp":1759773202640,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688052","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T15:39:28Z","timestamp":1728401968000},"page":"790-792","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Data Efficiency for Recommenders and LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1228-746X","authenticated-orcid":false,"given":"Noveen","family":"Sachdeva","sequence":"first","affiliation":[{"name":"Google DeepMind, Google DeepMind, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8045-3717","authenticated-orcid":false,"given":"Benjamin","family":"Coleman","sequence":"additional","affiliation":[{"name":"Google DeepMind, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8795-3665","authenticated-orcid":false,"given":"Wang-Cheng","family":"Kang","sequence":"additional","affiliation":[{"name":"n\/a, Google DeepMind, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6863-8073","authenticated-orcid":false,"given":"Jianmo","family":"Ni","sequence":"additional","affiliation":[{"name":"Deepmind, Google DeepMind, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8350-8528","authenticated-orcid":false,"given":"James","family":"Caverlee","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Texas A&M University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9563-554X","authenticated-orcid":false,"given":"Lichan","family":"Hong","sequence":"additional","affiliation":[{"name":"Google DeepMind, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3230-5338","authenticated-orcid":false,"given":"Ed","family":"Chi","sequence":"additional","affiliation":[{"name":"Google DeepMind, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7943-8328","authenticated-orcid":false,"given":"Derek Zhiyuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Google DeepMind, Google DeepMind, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication. arXiv preprint arXiv:2303.09540","author":"Abbas Amro","year":"2023","unstructured":"Amro Abbas, Kushal Tirumala, D\u00e1niel Simig, Surya Ganguli, and Ari\u00a0S Morcos. 2023. SemDeDup: Data-efficient learning at web-scale through semantic deduplication. arXiv preprint arXiv:2303.09540 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"A Survey on Data Selection for Language Models. arXiv preprint arXiv:2402.16827","author":"Albalak Alon","year":"2024","unstructured":"Alon Albalak, Yanai Elazar, Sang\u00a0Michael Xie, Shayne Longpre, Nathan Lambert, Xinyi Wang, Niklas Muennighoff, Bairu Hou, Liangming Pan, Haewon Jeong, 2024. A Survey on Data Selection for Language Models. arXiv preprint arXiv:2402.16827 (2024)."},{"key":"e_1_3_2_1_3_1","first-page":"30016","article-title":"An empirical analysis of compute-optimal large language model training","volume":"35","author":"Hoffmann Jordan","year":"2022","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las\u00a0Casas, Lisa\u00a0Anne Hendricks, Johannes Welbl, Aidan Clark, 2022. An empirical analysis of compute-optimal large language model training. Advances in Neural Information Processing Systems 35 (2022), 30016\u201330030.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","volume-title":"Giulio Zhou, David\u00a0G Andersen, Jeffrey Dean, Gregory\u00a0R Ganger, Gauri Joshi, Michael Kaminksy, Michael Kozuch","author":"Jiang H","year":"2019","unstructured":"Angela\u00a0H Jiang, Daniel L-K Wong, Giulio Zhou, David\u00a0G Andersen, Jeffrey Dean, Gregory\u00a0R Ganger, Gauri Joshi, Michael Kaminksy, Michael Kozuch, Zachary\u00a0C Lipton, 2019. Accelerating deep learning by focusing on the biggest losers. arXiv preprint arXiv:1910.00762 (2019)."},{"volume-title":"Self-Attentive Sequential Recommendation. In 2018 IEEE International Conference on Data Mining.","author":"Kang W.","key":"e_1_3_2_1_5_1","unstructured":"W. Kang and J. McAuley. 2018. Self-Attentive Sequential Recommendation. In 2018 IEEE International Conference on Data Mining."},{"key":"e_1_3_2_1_6_1","volume-title":"Conference on Learning Theory. PMLR","author":"Karnin Zohar","year":"2019","unstructured":"Zohar Karnin and Edo Liberty. 2019. Discrepancy, coresets, and sketches in machine learning. In Conference on Learning Theory. PMLR, 1975\u20131993."},{"key":"e_1_3_2_1_7_1","volume-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv e-prints","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter\u00a0J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv e-prints (2019). arxiv:1910.10683"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_9_1","volume-title":"How to Train Data-Efficient LLMs. arXiv preprint arXiv:2402.09668","author":"Sachdeva Noveen","year":"2024","unstructured":"Noveen Sachdeva, Benjamin Coleman, Wang-Cheng Kang, Jianmo Ni, Lichan Hong, Ed\u00a0H Chi, James Caverlee, Julian McAuley, and Derek\u00a0Zhiyuan Cheng. 2024. How to Train Data-Efficient LLMs. arXiv preprint arXiv:2402.09668 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Farzi data: Autoregressive data distillation. arXiv preprint arXiv:2310.09983","author":"Sachdeva Noveen","year":"2023","unstructured":"Noveen Sachdeva, Zexue He, Wang-Cheng Kang, Jianmo Ni, Derek\u00a0Zhiyuan Cheng, and Julian McAuley. 2023. Farzi data: Autoregressive data distillation. arXiv preprint arXiv:2310.09983 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Data Distillation: A Survey. Transactions on Machine Learning Research","author":"Sachdeva Noveen","year":"2023","unstructured":"Noveen Sachdeva and Julian McAuley. 2023. Data Distillation: A Survey. Transactions on Machine Learning Research (2023). Survey Certification."},{"key":"e_1_3_2_1_12_1","volume-title":"Svp-cf: Selection via proxy for collaborative filtering data. arXiv preprint arXiv:2107.04984","author":"Sachdeva Noveen","year":"2021","unstructured":"Noveen Sachdeva, Carole-Jean Wu, and Julian McAuley. 2021. Svp-cf: Selection via proxy for collaborative filtering data. arXiv preprint arXiv:2107.04984 (2021)."},{"key":"e_1_3_2_1_13_1","first-page":"19523","article-title":"Beyond neural scaling laws: beating power law scaling via data pruning","volume":"35","author":"Sorscher Ben","year":"2022","unstructured":"Ben Sorscher, Robert Geirhos, Shashank Shekhar, Surya Ganguli, and Ari Morcos. 2022. Beyond neural scaling laws: beating power law scaling via data pruning. Advances in Neural Information Processing Systems 35 (2022), 19523\u201319536.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"D4: Improving llm pretraining via document de-duplication and diversification. Advances in Neural Information Processing Systems 36","author":"Tirumala Kushal","year":"2024","unstructured":"Kushal Tirumala, Daniel Simig, Armen Aghajanyan, and Ari Morcos. 2024. D4: Improving llm pretraining via document de-duplication and diversification. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations. arXiv preprint arXiv:2402.17152","author":"Zhai Jiaqi","year":"2024","unstructured":"Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Michael He, 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_16_1","volume-title":"A survey of large language models. arXiv preprint arXiv:2303.18223","author":"Zhao Wayne\u00a0Xin","year":"2023","unstructured":"Wayne\u00a0Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Bari Italy","acronym":"RecSys '24"},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688052","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:29Z","timestamp":1750294709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":16,"alternative-id":["10.1145\/3640457.3688052","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688052","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}