{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T22:02:57Z","timestamp":1761861777250,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP220103717"],"award-info":[{"award-number":["DP220103717"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3485447.3512072","type":"proceedings-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T05:11:23Z","timestamp":1650863483000},"page":"2348-2359","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Off-policy Learning over Heterogeneous Information for Recommendation"],"prefix":"10.1145","author":[{"given":"Xiangmeng","family":"Wang","sequence":"first","affiliation":[{"name":"University of Technology Sydney, Australia"}]},{"given":"Qian","family":"Li","sequence":"additional","affiliation":[{"name":"Curtin University, Australia"}]},{"given":"Dianer","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Australia"}]},{"given":"Guandong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Australia"}]}],"member":"320","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"M\u00a0Mehdi Afsar Trafford Crump and Behrouz Far. 2021. Reinforcement learning based recommender systems: A survey. arXiv preprint arXiv:2101.06286(2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331199"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939718"},{"key":"e_1_3_2_1_4_1","article-title":"Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising.","volume":"14","author":"Bottou L\u00e9on","year":"2013","unstructured":"L\u00e9on Bottou, Jonas Peters, Joaquin Qui\u00f1onero-Candela, Denis\u00a0X Charles, D\u00a0Max Chickering, Elon Portugaly, Dipankar Ray, Patrice Simard, and Ed Snelson. 2013. Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising.Journal of Machine Learning Research 14, 11 (2013).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_5_1","unstructured":"Jiawei Chen Hande Dong Xiang Wang Fuli Feng Meng Wang and Xiangnan He. 2020. Bias and debias in recommender system: A survey and future directions. arXiv preprint arXiv:2010.03240(2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Weijian Chen Yulong Gu Zhaochun Ren Xiangnan He Hongtao Xie Tong Guo Dawei Yin and Yongdong Zhang. 2019. Semi-supervised User Profiling with Heterogeneous Graph Attention Networks.. In IJCAI Vol.\u00a019. 2116\u20132122.","DOI":"10.24963\/ijcai.2019\/293"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159668"},{"key":"e_1_3_2_1_9_1","unstructured":"Xiaocong Chen Lina Yao Julian McAuley Guangling Zhou and Xianzhi Wang. 2021. A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions. arXiv preprint arXiv:2109.03540(2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3411754","article-title":"Block-Aware Item Similarity Models for Top-N Recommendation","volume":"38","author":"Chen Yifan","year":"2020","unstructured":"Yifan Chen, Yang Wang, Xiang Zhao, Jie Zou, and Maarten\u00a0De Rijke. 2020. Block-Aware Item Similarity Models for Top-N Recommendation. ACM Transactions on Information Systems (TOIS) 38, 4 (2020), 1\u201326.","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_12_1","unstructured":"Junyoung Chung Caglar Gulcehre KyungHyun Cho and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555(2014)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372851"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09744-1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098036"},{"key":"e_1_3_2_1_17_1","volume-title":"Adaptive subgradient methods for online learning and stochastic optimization.Journal of machine learning research 12, 7","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization.Journal of machine learning research 12, 7 (2011)."},{"key":"e_1_3_2_1_18_1","unstructured":"Tri\u00a0Dung Duong Qian Li and Guandong Xu. 2021. Prototype-based Counterfactual Explanation for Causal Classification. arXiv preprint arXiv:2105.00703(2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Stochastic Intervention for Causal Effect Estimation. In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138.","author":"Duong Tri\u00a0Dung","year":"2021","unstructured":"Tri\u00a0Dung Duong, Qian Li, and Guandong Xu. 2021. Stochastic Intervention for Causal Effect Estimation. In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186183"},{"key":"e_1_3_2_1_21_1","volume-title":"S1","author":"Flaxman Seth","year":"2016","unstructured":"Seth Flaxman, Sharad Goel, and Justin\u00a0M Rao. 2016. Filter bubbles, echo chambers, and online news consumption. Public opinion quarterly 80, S1 (2016), 298\u2013320."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1994.8753425"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"volume-title":"Supervised sequence labelling with recurrent neural networks","author":"Graves Alex","key":"e_1_3_2_1_24_1","unstructured":"Alex Graves. 2012. Long short-term memory. In Supervised sequence labelling with recurrent neural networks. Springer, 37\u201345."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371827"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/0471722146"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219965"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330790"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474247"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403175"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Learning Representations.","author":"Joachims Thorsten","year":"2018","unstructured":"Thorsten Joachims, Adith Swaminathan, and Maarten de Rijke. 2018. Deep learning with logged bandit feedback. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-018-0138-8"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401237"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481900"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806532"},{"key":"e_1_3_2_1_36_1","volume-title":"Be Causal: De-biasing Social Network Confounding in Recommendation. arXiv preprint arXiv:2105.07775(2021).","author":"Li Qian","year":"2021","unstructured":"Qian Li, Xiangmeng Wang, and Guandong Xu. 2021. Be Causal: De-biasing Social Network Confounding in Recommendation. arXiv preprint arXiv:2105.07775(2021)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298483.3298556"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3118542"},{"key":"e_1_3_2_1_39_1","unstructured":"Qian Li Zhichao Wang Shaowu Liu Gang Li and Guandong Xu. 2021. Deep Treatment-Adaptive Network for Causal Inference. arXiv preprint arXiv:2112.13502(2021)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106170"},{"key":"e_1_3_2_1_41_1","volume-title":"Artificial convolution neural network for medical image pattern recognition. Neural networks 8, 7-8","author":"Lo B","year":"1995","unstructured":"Shih-Chung\u00a0B Lo, Heang-Ping Chan, Jyh-Shyan Lin, Huai Li, Matthew\u00a0T Freedman, and Seong\u00a0K Mun. 1995. Artificial convolution neural network for medical image pattern recognition. Neural networks 8, 7-8 (1995), 1201\u20131214."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.317"},{"key":"e_1_3_2_1_44_1","volume-title":"Debiased Off-Policy Evaluation for Recommendation Systems. In Fifteenth ACM Conference on Recommender Systems. 372\u2013379","author":"Narita Yusuke","year":"2021","unstructured":"Yusuke Narita, Shota Yasui, and Kohei Yata. 2021. Debiased Off-Policy Evaluation for Recommendation Systems. In Fifteenth ACM Conference on Recommender Systems. 372\u2013379."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57454-7_15"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3473320"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403121"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117709"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.08.008"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_1_52_1","volume-title":"International Conference on Machine Learning. PMLR, 814\u2013823","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015. Counterfactual risk minimization: Learning from logged bandit feedback. In International Conference on Machine Learning. PMLR, 814\u2013823."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_54_1","volume-title":"International Conference on Machine Learning. PMLR, 2139\u20132148","author":"Thomas Philip","year":"2016","unstructured":"Philip Thomas and Emma Brunskill. 2016. Data-efficient off-policy policy evaluation for reinforcement learning. In International Conference on Machine Learning. PMLR, 2139\u20132148."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340631.3398666"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_2"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_14"},{"key":"e_1_3_2_1_58_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3","author":"Williams J","year":"1992","unstructured":"Ronald\u00a0J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3 (1992), 229\u2013256."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835837"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16579"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16580"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_1_63_1","unstructured":"Guandong Xu Tri\u00a0Dung Duong Qian Li Shaowu Liu and Xianzhi Wang. 2020. Causality learning: a new perspective for interpretable machine learning. arXiv preprint arXiv:2006.16789(2020)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_65_1","unstructured":"Houssam Zenati Alberto Bietti Matthieu Martin Eustache Diemert and Julien Mairal. 2020. Counterfactual learning of continuous stochastic policies. arXiv preprint arXiv:2004.11722(2020)."},{"key":"e_1_3_2_1_66_1","unstructured":"Houssam Zenati Alberto Bietti Matthieu Martin Eustache Diemert and Julien Mairal. 2021. Counterfactual Learning of Stochastic Policies with Continuous Actions: from Models to Offline Evaluation. (2021)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"}],"event":{"name":"WWW '22: The ACM Web Conference 2022","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Virtual Event, Lyon France","acronym":"WWW '22"},"container-title":["Proceedings of the ACM Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512072","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485447.3512072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:07Z","timestamp":1750188607000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512072"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":68,"alternative-id":["10.1145\/3485447.3512072","10.1145\/3485447"],"URL":"https:\/\/doi.org\/10.1145\/3485447.3512072","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-04-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}