{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:03:14Z","timestamp":1775815394826,"version":"3.50.1"},"reference-count":12,"publisher":"Association for Computing Machinery (ACM)","issue":"12","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:p>\n            We demonstrate\n            <jats:bold>ModsNet<\/jats:bold>\n            , a search tool for pre-trained data science\n            <jats:bold>MOD<\/jats:bold>\n            el\n            <jats:bold>s<\/jats:bold>\n            recommendatio\n            <jats:bold>N<\/jats:bold>\n            using\n            <jats:bold>E<\/jats:bold>\n            xamplar da\n            <jats:bold>T<\/jats:bold>\n            aset. Given a set of pre-trained data science models, an \"example\" input dataset, and a user-specified performance metric, ModsNet answers the following query:\n            <jats:italic>\"what are top-k models that have the best expected performance for the input data?\"<\/jats:italic>\n            The need for searching high-quality pre-trained models is evident in data-driven analysis. Inspired by \"query by example\" paradigm, ModsNet does not require users to write complex queries, but only provide an \"examplar\" dataset, a task description, and a performance measure as input, and can automatically suggest top-\n            <jats:italic>k<\/jats:italic>\n            matching models that are expected to have desirable performance to perform the task over the provided sample dataset. ModsNet utilizes a knowledge graph to integrate model performances over datasets and synchronizes it with a bipartite graph neural network to\n            <jats:italic>estimate<\/jats:italic>\n            model performance, reduce inference cost, and promptly respond to top-\n            <jats:italic>k<\/jats:italic>\n            model search queries. To cope with strict cold-start (upon receiving a new dataset when no historical performance of registered models are observed), it performs a dynamic, cost-bounded \"probe-and-select\" strategy to incrementally identify promising models. We demonstrate the application of ModsNet in enabling efficient scientific data analysis.\n          <\/jats:p>","DOI":"10.14778\/3685800.3685899","type":"journal-article","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T17:25:21Z","timestamp":1731086721000},"page":"4457-4460","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ModsNet: Performance-Aware Top-\n            <i>k<\/i>\n            Model Search Using Exemplar Datasets"],"prefix":"10.14778","volume":"17","author":[{"given":"Mengying","family":"Wang","sequence":"first","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanchao","family":"Ma","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Guan","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyang","family":"Bian","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haolai","family":"Che","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Daundkar","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alp","family":"Sehirlioglu","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghui","family":"Wu","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"https:\/\/github.com\/crux-project\/crux-recommendModels","year":"2024","unstructured":"2024. Github. (2024). https:\/\/github.com\/crux-project\/crux-recommendModels"},{"key":"e_1_2_1_2_1","unstructured":"2024. Hugging Face - The AI Community Building the Future. (2024). https:\/\/huggingface.co\/"},{"key":"e_1_2_1_3_1","unstructured":"2024. Kaggle: Your Home for Data Science. (2024). https:\/\/www.kaggle.com\/"},{"key":"e_1_2_1_4_1","volume-title":"Scalable graph neural networks via bidirectional propagation. NeurIPS","author":"Chen Ming","year":"2020","unstructured":"Ming Chen, Zhewei Wei, Bolin Ding, Yaliang Li, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen. 2020. Scalable graph neural networks via bidirectional propagation. NeurIPS (2020)."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_2_1_7_1","unstructured":"Simon Kornblith Mohammad Norouzi Honglak Lee and Geoffrey Hinton. 2019. Similarity of neural network representations revisited. In ICML. 3519--3529."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.108101"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-022-00441-7"},{"key":"e_1_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Mengying Wang Sheng Guan Hanchao Ma Yiyang Bian Haolai Che Abhishek Daundkar Alp Sehirlioglu and Yinghui Wu. 2023. Selecting Top-k Data Science Models by Example Dataset. In CIKM.","DOI":"10.1145\/3583780.3615051"},{"key":"e_1_2_1_11_1","volume-title":"CRUX: Crowdsourced Materials Science Resource and Workflow Exploration. In CIKM.","author":"Wang Mengying","year":"2022","unstructured":"Mengying Wang, Hanchao Ma, Abhishek Daundkar, Sheng Guan, Yiyang Bian, Alpi Sehirlioglu, and Yinghui Wu. 2022. CRUX: Crowdsourced Materials Science Resource and Workflow Exploration. In CIKM."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532000"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3685800.3685899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:35:07Z","timestamp":1735623307000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3685800.3685899"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":12,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.14778\/3685800.3685899"],"URL":"https:\/\/doi.org\/10.14778\/3685800.3685899","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"2024-11-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}