{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T01:30:22Z","timestamp":1781055022686,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709417","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"2525-2535","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SSE: Multimodal Semantic Data Selection and Enrichment for Industrial-scale Data Assimilation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9416-680X","authenticated-orcid":false,"given":"Maying","family":"Shen","sequence":"first","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4765-8478","authenticated-orcid":false,"given":"Nadine","family":"Chang","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6011-3686","authenticated-orcid":false,"given":"Sifei","family":"Liu","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7535-6322","authenticated-orcid":false,"given":"Jose M.","family":"Alvarez","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Deep batch active learning by diverse, uncertain gradient lower bounds. arXiv preprint arXiv:1906.03671","author":"Ash Jordan T","year":"2019","unstructured":"Jordan T Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, and Alekh Agarwal. 2019. Deep batch active learning by diverse, uncertain gradient lower bounds. arXiv preprint arXiv:1906.03671 (2019)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2017.03.131"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_2_4_1","volume-title":"Thinking like an annotator: Generation of dataset labeling instructions. arXiv preprint arXiv:2306.14035","author":"Chang Nadine","year":"2023","unstructured":"Nadine Chang, Francesco Ferroni, Michael J Tarr, Martial Hebert, and Deva Ramanan. 2023. Thinking like an annotator: Generation of dataset labeling instructions. arXiv preprint arXiv:2306.14035 (2023)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Jiwoong Choi Ismail Elezi Hyuk-Jae Lee Clement Farabet and Jose M Alvarez. 2021. Active learning for deep object detection via probabilistic modeling. In ICCV. 10264--10273.","DOI":"10.1109\/ICCV48922.2021.01010"},{"key":"e_1_3_2_2_6_1","unstructured":"Vitaly Feldman and Chiyuan Zhang. [n. d.]. What neural networks memorize and why: Discovering the long tail via influence estimation. NeurIPS ( [n. d.])."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Sachin Goyal Pratyush Maini Zachary C Lipton Aditi Raghunathan and J Zico Kolter. 2024. Scaling Laws for Data Filtering--Data Curation cannot be Compute Agnostic. In CVPR. 22702--22711.","DOI":"10.1109\/CVPR52733.2024.02142"},{"key":"e_1_3_2_2_8_1","volume-title":"Piotr Dollar, and Ross Girshick","author":"Gupta Agrim","year":"2019","unstructured":"Agrim Gupta, Piotr Dollar, and Ross Girshick. 2019. Lvis: A dataset for large vocabulary instance segmentation. In CVPR. 5356--5364."},{"key":"e_1_3_2_2_9_1","volume-title":"Scalable active learning for object detection. In 2020 IEEE intelligent vehicles symposium","author":"Haussmann Elmar","unstructured":"Elmar Haussmann, Michele Fenzi, Kashyap Chitta, Jan Ivanecky, Hanson Xu, Donna Roy, Akshita Mittel, Nicolas Koumchatzky, Clement Farabet, and Jose M Alvarez. 2020. Scalable active learning for object detection. In 2020 IEEE intelligent vehicles symposium. IEEE, 1430--1435."},{"key":"e_1_3_2_2_10_1","volume-title":"Localization-aware active learning for object detection","author":"Kao Chieh-Chi","unstructured":"Chieh-Chi Kao, Teng-Yok Lee, Pradeep Sen, and Ming-Yu Liu. 2019. Localization-aware active learning for object detection. In ACCV. Springer, 506--522."},{"key":"e_1_3_2_2_11_1","volume-title":"NeurIPS","volume":"30","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_2_12_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023. Improved Baselines with Visual Instruction Tuning."},{"key":"e_1_3_2_2_13_1","first-page":"7498","article-title":"Simple and principled uncertainty estimation with deterministic deep learning via distance awareness","volume":"33","author":"Liu Jeremiah","year":"2020","unstructured":"Jeremiah Liu, Zi Lin, Shreyas Padhy, Dustin Tran, Tania Bedrax Weiss, and Balaji Lakshminarayanan. 2020. Simple and principled uncertainty estimation with deterministic deep learning via distance awareness. NeurIPS, Vol. 33 (2020), 7498--7512.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_14_1","volume-title":"Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786","author":"Lu Yao","year":"2021","unstructured":"Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, and Pontus Stenetorp. 2021. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786 (2021)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00681"},{"key":"e_1_3_2_2_16_1","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume":"34","author":"Paul Mansheej","year":"2021","unstructured":"Mansheej Paul, Surya Ganguli, and Gintare Karolina Dziugaite. 2021. Deep learning on a data diet: Finding important examples early in training. NeurIPS, Vol. 34 (2021), 20596--20607.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_17_1","volume-title":"Mehdi Sajjadi, Xin Liu, Hsuan-Chu Lin, Bor-Jeng Chen, Giang Truong, Chao Fang, et al.","author":"Pham Trung","year":"2023","unstructured":"Trung Pham, Mehran Maghoumi, Wanli Jiang, Bala Siva Sashank Jujjavarapu, Mehdi Sajjadi, Xin Liu, Hsuan-Chu Lin, Bor-Jeng Chen, Giang Truong, Chao Fang, et al. 2023. NVAutoNet: Fast and Accurate 360 3D Visual Perception For Self Driving. arXiv preprint arXiv:2303.12976 (2023)."},{"key":"e_1_3_2_2_18_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_19_1","first-page":"91","article-title":"Deep active learning for object detection","volume":"362","author":"Roy Soumya","year":"2018","unstructured":"Soumya Roy, Asim Unmesh, and Vinay P Namboodiri. 2018. Deep active learning for object detection.. In BMVC, Vol. 362. 91.","journal-title":"BMVC"},{"key":"e_1_3_2_2_20_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","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, et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25278--25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_21_1","volume-title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting. arXiv preprint arXiv:2310.11324","author":"Sclar Melanie","year":"2023","unstructured":"Melanie Sclar, Yejin Choi, Yulia Tsvetkov, and Alane Suhr. 2023. Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting. arXiv preprint arXiv:2310.11324 (2023)."},{"key":"e_1_3_2_2_22_1","volume-title":"Active learning for convolutional neural networks: A core-set approach. arXiv preprint arXiv:1708.00489","author":"Sener Ozan","year":"2017","unstructured":"Ozan Sener and Silvio Savarese. 2017. Active learning for convolutional neural networks: A core-set approach. arXiv preprint arXiv:1708.00489 (2017)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssresearch.2022.102817"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Eric Slyman Stefan Lee Scott Cohen and Kushal Kafle. 2024. FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication. In CVPR. 13905--13916.","DOI":"10.1109\/CVPR52733.2024.01319"},{"key":"e_1_3_2_2_25_1","volume-title":"Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications","author":"Smith Leslie N","year":"2019","unstructured":"Leslie N Smith and Nicholay Topin. 2019. Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications, Vol. 11006. SPIE, 369--386."},{"key":"e_1_3_2_2_26_1","volume-title":"Mpnet: Masked and permuted pre-training for language understanding. Advances in neural information processing systems","author":"Song Kaitao","year":"2020","unstructured":"Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. Mpnet: Masked and permuted pre-training for language understanding. Advances in neural information processing systems, Vol. 33 (2020), 16857--16867."},{"key":"e_1_3_2_2_27_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. NeurIPS, Vol. 35 (2022), 19523--19536.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_28_1","volume-title":"NeurIPS","volume":"36","author":"Tan Haoru","year":"2024","unstructured":"Haoru Tan, Sitong Wu, Fei Du, Yukang Chen, Zhibin Wang, Fan Wang, and Xiaojuan Qi. 2024. Data pruning via moving-one-sample-out. NeurIPS, Vol. 36 (2024)."},{"key":"e_1_3_2_2_29_1","volume-title":"Adam Trischler, Yoshua Bengio, and Geoffrey J Gordon.","author":"Toneva Mariya","year":"2018","unstructured":"Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, and Geoffrey J Gordon. 2018. An empirical study of example forgetting during deep neural network learning. arXiv preprint arXiv:1812.05159 (2018)."},{"key":"e_1_3_2_2_30_1","volume-title":"Deep sub-ensembles for fast uncertainty estimation in image classification. arXiv preprint arXiv: 191008168.(2019) doi: 10.48550. arXiv","author":"Valdenegro-Toro Matias","year":"1910","unstructured":"Matias Valdenegro-Toro. 1910. Deep sub-ensembles for fast uncertainty estimation in image classification. arXiv preprint arXiv: 191008168.(2019) doi: 10.48550. arXiv (1910)."},{"key":"e_1_3_2_2_31_1","volume-title":"Mind your format: Towards consistent evaluation of in-context learning improvements. arXiv preprint arXiv:2401.06766","author":"Voronov Anton","year":"2024","unstructured":"Anton Voronov, Lena Wolf, and Max Ryabinin. 2024. Mind your format: Towards consistent evaluation of in-context learning improvements. arXiv preprint arXiv:2401.06766 (2024)."},{"key":"e_1_3_2_2_32_1","volume-title":"Batchensemble: an alternative approach to efficient ensemble and lifelong learning. arXiv preprint arXiv:2002.06715","author":"Wen Yeming","year":"2020","unstructured":"Yeming Wen, Dustin Tran, and Jimmy Ba. 2020. Batchensemble: an alternative approach to efficient ensemble and lifelong learning. arXiv preprint arXiv:2002.06715 (2020)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Donggeun Yoo and In So Kweon. 2019. Learning loss for active learning. In CVPR. 93--102.","DOI":"10.1109\/CVPR.2019.00018"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709417","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:34:42Z","timestamp":1755358482000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":33,"alternative-id":["10.1145\/3690624.3709417","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709417","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}