Introducing LensKit-Auto, an experimental automated recommender system (AutoRecSys) toolkit

Introducing LensKit-Auto, an experimental automated recommender system (AutoRecSys) toolkit. Vente, T., Ekstrand, M., & Beel, J. In Proceedings of the 17th ACM Conference on Recommender Systems, of RecSys '23, pages 1212–1216, New York, NY, USA, September, 2023. Association for Computing Machinery.

Paper doi abstract bibtex 1 download

LensKit is one of the first and most popular Recommender System libraries. While LensKit offers a wide variety of features, it does not include any optimization strategies or guidelines on how to select and tune LensKit algorithms. LensKit developers have to manually include third-party libraries into their experimental setup or implement optimization strategies by hand to optimize hyperparameters. We found that 63.6% (21 out of 33) of papers using LensKit algorithms for their experiments did not select algorithms or tune hyperparameters. Non-optimized models represent poor baselines and produce less meaningful research results. This demo introduces LensKit-Auto. LensKit-Auto automates the entire Recommender System pipeline and enables LensKit developers to automatically select, optimize, and ensemble LensKit algorithms.

@inproceedings{vente_introducing_2023,
	address = {New York, NY, USA},
	series = {{RecSys} '23},
	title = {Introducing {LensKit}-{Auto}, an experimental automated recommender system ({AutoRecSys}) toolkit},
	isbn = {9798400702419},
	url = {https://dl.acm.org/doi/10.1145/3604915.3610656},
	doi = {10.1145/3604915.3610656},
	abstract = {LensKit is one of the first and most popular Recommender System libraries. While LensKit offers a wide variety of features, it does not include any optimization strategies or guidelines on how to select and tune LensKit algorithms. LensKit developers have to manually include third-party libraries into their experimental setup or implement optimization strategies by hand to optimize hyperparameters. We found that 63.6\% (21 out of 33) of papers using LensKit algorithms for their experiments did not select algorithms or tune hyperparameters. Non-optimized models represent poor baselines and produce less meaningful research results. This demo introduces LensKit-Auto. LensKit-Auto automates the entire Recommender System pipeline and enables LensKit developers to automatically select, optimize, and ensemble LensKit algorithms.},
	urldate = {2023-09-18},
	booktitle = {Proceedings of the 17th {ACM} {Conference} on {Recommender} {Systems}},
	publisher = {Association for Computing Machinery},
	author = {Vente, Tobias and Ekstrand, Michael and Beel, Joeran},
	month = sep,
	year = {2023},
	keywords = {Algorithm Selection, AutoRecSys, Automated Recommender Systems, CASH, Hyperparameter Optimization, Recommender Systems},
	pages = {1212--1216},
}

Downloads: 1

{"_id":"vSW4sqMeQh9h4cteJ","bibbaseid":"vente-ekstrand-beel-introducinglenskitautoanexperimentalautomatedrecommendersystemautorecsystoolkit-2023","author_short":["Vente, T.","Ekstrand, M.","Beel, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","series":"RecSys '23","title":"Introducing LensKit-Auto, an experimental automated recommender system (AutoRecSys) toolkit","isbn":"9798400702419","url":"https://dl.acm.org/doi/10.1145/3604915.3610656","doi":"10.1145/3604915.3610656","abstract":"LensKit is one of the first and most popular Recommender System libraries. While LensKit offers a wide variety of features, it does not include any optimization strategies or guidelines on how to select and tune LensKit algorithms. LensKit developers have to manually include third-party libraries into their experimental setup or implement optimization strategies by hand to optimize hyperparameters. We found that 63.6% (21 out of 33) of papers using LensKit algorithms for their experiments did not select algorithms or tune hyperparameters. Non-optimized models represent poor baselines and produce less meaningful research results. This demo introduces LensKit-Auto. LensKit-Auto automates the entire Recommender System pipeline and enables LensKit developers to automatically select, optimize, and ensemble LensKit algorithms.","urldate":"2023-09-18","booktitle":"Proceedings of the 17th ACM Conference on Recommender Systems","publisher":"Association for Computing Machinery","author":[{"propositions":[],"lastnames":["Vente"],"firstnames":["Tobias"],"suffixes":[]},{"propositions":[],"lastnames":["Ekstrand"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Beel"],"firstnames":["Joeran"],"suffixes":[]}],"month":"September","year":"2023","keywords":"Algorithm Selection, AutoRecSys, Automated Recommender Systems, CASH, Hyperparameter Optimization, Recommender Systems","pages":"1212–1216","bibtex":"@inproceedings{vente_introducing_2023,\n\taddress = {New York, NY, USA},\n\tseries = {{RecSys} '23},\n\ttitle = {Introducing {LensKit}-{Auto}, an experimental automated recommender system ({AutoRecSys}) toolkit},\n\tisbn = {9798400702419},\n\turl = {https://dl.acm.org/doi/10.1145/3604915.3610656},\n\tdoi = {10.1145/3604915.3610656},\n\tabstract = {LensKit is one of the first and most popular Recommender System libraries. While LensKit offers a wide variety of features, it does not include any optimization strategies or guidelines on how to select and tune LensKit algorithms. LensKit developers have to manually include third-party libraries into their experimental setup or implement optimization strategies by hand to optimize hyperparameters. We found that 63.6\\% (21 out of 33) of papers using LensKit algorithms for their experiments did not select algorithms or tune hyperparameters. Non-optimized models represent poor baselines and produce less meaningful research results. This demo introduces LensKit-Auto. LensKit-Auto automates the entire Recommender System pipeline and enables LensKit developers to automatically select, optimize, and ensemble LensKit algorithms.},\n\turldate = {2023-09-18},\n\tbooktitle = {Proceedings of the 17th {ACM} {Conference} on {Recommender} {Systems}},\n\tpublisher = {Association for Computing Machinery},\n\tauthor = {Vente, Tobias and Ekstrand, Michael and Beel, Joeran},\n\tmonth = sep,\n\tyear = {2023},\n\tkeywords = {Algorithm Selection, AutoRecSys, Automated Recommender Systems, CASH, Hyperparameter Optimization, Recommender Systems},\n\tpages = {1212--1216},\n}\n\n","author_short":["Vente, T.","Ekstrand, M.","Beel, J."],"key":"vente_introducing_2023","id":"vente_introducing_2023","bibbaseid":"vente-ekstrand-beel-introducinglenskitautoanexperimentalautomatedrecommendersystemautorecsystoolkit-2023","role":"author","urls":{"Paper":"https://dl.acm.org/doi/10.1145/3604915.3610656"},"keyword":["Algorithm Selection","AutoRecSys","Automated Recommender Systems","CASH","Hyperparameter Optimization","Recommender Systems"],"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/6655/collections/3TB3KT36/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","dataSources":["ca4t6HZh8piBqYaYM","7KNAjxiv2tsagmbgY"],"keywords":["algorithm selection","autorecsys","automated recommender systems","cash","hyperparameter optimization","recommender systems"],"search_terms":["introducing","lenskit","auto","experimental","automated","recommender","system","autorecsys","toolkit","vente","ekstrand","beel"],"title":"Introducing LensKit-Auto, an experimental automated recommender system (AutoRecSys) toolkit","year":2023,"downloads":1}