{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:23:18Z","timestamp":1755926598409},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tkde.2021.3098898","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T22:19:44Z","timestamp":1627337984000},"page":"1-1","source":"Crossref","is-referenced-by-count":9,"title":["AliExpress Learning-To-Rank: Maximizing Online Model Performance without Going Online"],"prefix":"10.1109","author":[{"given":"Guangda","family":"Huzhang","sequence":"first","affiliation":[]},{"given":"Zhenjia","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Yongqing","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Yawen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Weijie","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Wen-Ji","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Da","sequence":"additional","affiliation":[]},{"given":"Anxiang","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Han","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Zhi-Hua","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","article-title":"RecoGym: A reinforcement learning environment for the problem of product recommendation in online advertising","author":"Rohde","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2532508.2532511"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959176"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1125451.1125659"},{"key":"ref5","article-title":"Sequential evaluation and generation framework for combinatorial recommender system","author":"Wang","year":"2019","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/518"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347000"},{"key":"ref8","article-title":"Seq2Slate: Re-ranking and slate optimization with RNNs","author":"Bello","year":"2018","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2008.929939"},{"key":"ref10","first-page":"897","article-title":"McRank: Learning to rank using multiple classification and gradient boosting","volume-title":"Proc. 21st Annu. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/9789812799524_0068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3023-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775067"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"ref15","first-page":"23","article-title":"From RankNet to LambdaRank to LambdaMART: An overview","volume":"11","author":"Burges","year":"2010","journal-title":"Learning"},{"key":"ref16","article-title":"BPR: Bayesian personalized ranking from implicit feedback","author":"Rendle","year":"2012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390306"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209985"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3016732"},{"issue":"2","key":"ref22","first-page":"430","article-title":"A survey of autoencoder-based recommender systems","volume-title":"Front. Comput. Sci.","volume":"14","author":"Zhang","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3341981.3344218"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330832"},{"key":"ref26","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref27","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref28","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209993"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to Reinforcement Learning","author":"Sutton","year":"1998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref33","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/360"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"ref36","article-title":"RecSim: A configurable simulation platform for recommender systems","author":"Ie","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018699"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331202"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210104"},{"key":"ref40","first-page":"1","article-title":"Buy 4 REINFORCE samples, get a baseline for free!","author":"Kool","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403345"},{"key":"ref43","first-page":"1","article-title":"Beyond greedy ranking: Slate optimization via List-CVAE","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Jiang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1341531.1341544"},{"key":"ref45","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357945"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.17184\/eac.9782813000873"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09495161.pdf?arnumber=9495161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:22:01Z","timestamp":1705015321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9495161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tkde.2021.3098898","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}