{"type":"ScholarlyArticle","title":"SemFORMS: Automatic Generation of Semantic Transforms By Mining Data Science Code","authors":[{"name":"Ibrahim Abdelaziz","slug":"ibrahim-abdelaziz","given":"Ibrahim","family":"Abdelaziz","affiliation":"Research Center , IBM Research"},{"name":"Julian Dolby","slug":"julian-dolby","given":"Julian","family":"Dolby","affiliation":"Research Center , IBM Research"},{"name":"Udayan Khurana","slug":"udayan-khurana","given":"Udayan","family":"Khurana","affiliation":"Research Center , IBM Research"},{"name":"Horst Samulowitz","slug":"horst-samulowitz","given":"Horst","family":"Samulowitz","affiliation":"Research Center , IBM Research"},{"name":"Kavitha Srinivas","slug":"kavitha-srinivas","given":"Kavitha","family":"Srinivas","affiliation":""}],"abstract":"Careful choice of feature transformations in a dataset can help predictive model performance, data understanding and data exploration. However, finding useful features is a challenge, and while recent Automated Machine Learning (AutoML) systems provide some limited automation for feature engineering or data exploration, it is still mostly done by humans. We demonstrate a system called SemFORMS (Semantic Transforms), which attempts to mine useful expressions for a dataset from access to a repository of code that may target the same dataset/similar dataset.  In many enterprises, numerous data scientists often work on the same or similar datasets, but are largely unaware of each other's work.  SemFORMS finds appropriate code from such a repository, and normalizes the code to be an actionable transform that can prepended into any AutoML pipeline.  We demonstrate SemFORMS operating over example datasets from the OpenML benchmarks where it sometimes leads to significant improvements in AutoML performance.","doi":"10.24963/ijcai.2023/827","url":"https://ijcai.org/proceedings/2023/827","pdf":"https://ijcai.org/proceedings/2023/0827.pdf","markdown":"https://ijcai.org/proceedings/2023/827.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/827","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Demo Track","track":"Demo Track","number":827,"pages":{"first":7106,"last":7109},"keywords":["Machine Learning: ML: Automated machine learning"],"videos":[],"references":[{"position":1,"raw":"[Abdelaziz et al., 2021] Ibrahim Abdelaziz, Julian Dolby, James P McCusker, and Kavitha Srinivas. A toolkit for generating code knowledge graphs. The Eleventh Interna- tional Conference on Knowledge Capture (K-CAP), 2021.","title":"A toolkit for generating code knowledge graphs","authors":"Ibrahim Abdelaziz, Julian Dolby, James P Mccusker, Kavitha Srinivas","year":"2021","venue":"The Eleventh International Conference on Knowledge Capture","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[He et al., 2018] Yeye He, Xu Chu, Kris Ganjam, Yu- dian Zheng, Vivek Narasayya, and Surajit Chaudhuri. Transform-data-by-example (tde) an extensible search en- gine for data transformations. Proceedings of the VLDB Endowment, 11(10):1165-1177, 2018.","title":"Transform-data-by-example (tde) an extensible search engine for data transformations","authors":"Yeye He, Xu Chu, Kris Ganjam, Yudian Zheng, Vivek Narasayya, Surajit Chaudhuri","year":"2018","venue":"Proceedings of the VLDB Endowment","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Jin et al., 2017] Zhongjun Jin, Michael R Anderson, Michael Cafarella, and HV Jagadish. Foofah: Transform- ing data by example. In Proceedings of the 2017 ACM International Conference on Management of Data, pages 683-698, 2017.","title":"Foofah: Transforming data by example","authors":"Jin","year":"2017","venue":"Proceedings of the 2017 ACM International Conference on Management of Data","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Kanter and Veeramachaneni, 2015] James Max Kanter and Kalyan Veeramachaneni. Deep feature synthesis: Towards automating data science endeavors. In 2015 IEEE interna- tional conference on data science and advanced analytics (DSAA), pages 1-10. IEEE, 2015.","title":"Deep feature synthesis: Towards automating data science endeavors","authors":"Veeramachaneni ; Kanter, Max James, Kalyan Kanter, Veeramachaneni","year":"2015","venue":"IEEE international conference on data science and advanced analytics (DSAA)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Kaul et al., 2017] Ambika Kaul, Saket Maheshwary, and Vikram Pudi. Autolearn-automated feature generation and selection. In 2017 IEEE International Conference on data mining (ICDM), pages 217-226. IEEE, 2017.","title":"Autolearn-automated feature generation and selection","authors":"Ambika Kaul, Saket Maheshwary, Vikram Pudi","year":"2017","venue":"IEEE International Conference on data mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ke et al., 2017] Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. Lightgbm: A highly efficient gradient boost- ing decision tree. Advances in neural information process- ing systems, 30:3146-3154, 2017.","title":"Lightgbm: A highly efficient gradient boosting decision tree","authors":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, Tie-Yan Liu","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Khurana et al., 2016] Udayan Khurana, Deepak Turaga, Horst Samulowitz, and Srinivasan Parthasarathy. Cognito: Automated feature engineering for supervised learning. In IEEE ICDM, pages 1304-1307, 2016.","title":"Cognito: Automated feature engineering for supervised learning","authors":"Udayan Khurana, Deepak Turaga, Horst Samulowitz, Srinivasan Parthasarathy","year":"2016","venue":"IEEE ICDM","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lam et al., 2021] Hoang Thanh Lam, Beat Buesser, Hong Min, Tran Ngoc Minh, Martin Wistuba, Udayan Khurana, Gregory Bramble, Theodoros Salonidis, Dakuo Wang, and Horst Samulowitz. Automated data science for relational data. In 2021 IEEE 37th International Conference on Data Engineering (ICDE), pages 2689-2692. IEEE, 2021.","title":"Automated data science for relational data","authors":"Thanh Hoang, Beat Lam, Hong Buesser, Tran Min, Martin Ngoc Minh, Udayan Wistuba, Gregory Khurana, Theodoros Bramble, Dakuo Salonidis, Horst Wang, Samulowitz","year":"2021","venue":"IEEE 37th International Conference on Data Engineering (ICDE)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Le and Gulwani, 2014] Vu Le and Sumit Gulwani. Flashex- tract: A framework for data extraction by examples. In Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation, pages 542-553, 2014.","title":"Flashextract: A framework for data extraction by examples","authors":"Le Vu, Sumit Gulwani","year":"2014","venue":"Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Psallidas et al., 2022] Fotis Psallidas, Yiwen Zhu, Bojan Karlas, Jordan Henkel, Matteo Interlandi, Subru Krishnan, Brian Kroth, Venkatesh Emani, Wentao Wu, Ce Zhang, Markus Weimer, Avrilia Floratou, Carlo Curino, and Kon- stantinos Karanasos. Data science through the looking glass: Analysis of millions of github notebooks and ml.net pipelines. SIGMOD Rec., 51(2):30-37, jul 2022.","title":"Data science through the looking glass: Analysis of millions of github notebooks and ml.net pipelines","authors":"Fotis Psallidas, Yiwen Zhu, Bojan Karlas, Jordan Henkel, Matteo Interlandi, Subru Krishnan, Brian Kroth, Venkatesh Emani, Wentao Wu, Ce Zhang, Markus Weimer, Avrilia Floratou, Carlo Curino, Konstantinos Karanasos","year":"2022","venue":"SIGMOD Rec","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Rehman, 2019] Mohammed Suhail Rehman. Towards un- derstanding data analysis workflows using a large note- book corpus. In Proceedings of the 2019 International Conference on Management of Data, SIGMOD '19, page 1841-1843, New York, NY, USA, 2019. Association for Computing Machinery.","title":"Towards understanding data analysis workflows using a large notebook corpus","authors":"Mohammed Suhail, Rehman","year":"2019","venue":"Proceedings of the 2019 International Conference on Management of Data, SIGMOD '19","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Yan and He, 2020] Cong Yan and Yeye He. Auto-suggest: Learning-to-recommend data preparation steps using data science notebooks. In Proceedings of the 2020 ACM SIG- MOD International Conference on Management of Data, pages 1539-1554, 2020.","title":"Auto-suggest: Learning-to-recommend data preparation steps using data science notebooks","authors":"Cong Yan, Yeye He","year":"2020","venue":"Proceedings of the 2020 ACM SIG-MOD International Conference on Management of Data","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}