{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:03:04Z","timestamp":1760598184944,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"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":[[2022,7,6]]},"DOI":"10.1145\/3477495.3532021","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:08Z","timestamp":1657206728000},"page":"1369-1378","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["MGPolicy"],"prefix":"10.1145","author":[{"given":"Xiangmeng","family":"Wang","sequence":"first","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}]},{"given":"Qian","family":"Li","sequence":"additional","affiliation":[{"name":"Curtin University, Perth, WA, Australia"}]},{"given":"Dianer","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}]},{"given":"Zhichao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}]},{"given":"Hongxu","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}]},{"given":"Guandong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_2_2_1","volume-title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions. arXiv preprint arXiv:2109.03540","author":"Chen Xiaocong","year":"2021","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 ). 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_2_3_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 De Rijke . 2020 . Block- Aware Item Similarity Models for Top-N Recommendation . ACM Transactions on Information Systems (TOIS) 38 , 4 (2020), 1 -- 26 . Yifan Chen, Yang Wang, Xiang Zhao, Jie Zou, and Maarten De Rijke. 2020. Block- Aware Item Similarity Models for Top-N Recommendation. ACM Transactions on Information Systems (TOIS) 38, 4 (2020), 1--26.","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09744-1"},{"key":"e_1_3_2_2_5_1","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","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). 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).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_6_1","volume-title":"Prototype-based Counter-factual Explanation for Causal Classification. arXiv preprint arXiv:2105.00703","author":"Duong Tri Dung","year":"2021","unstructured":"Tri Dung Duong , Qian Li , and Guandong Xu. 2021. Prototype-based Counter-factual Explanation for Causal Classification. arXiv preprint arXiv:2105.00703 ( 2021 ). Tri Dung Duong, Qian Li, and Guandong Xu. 2021. Prototype-based Counter-factual Explanation for Causal Classification. arXiv preprint arXiv:2105.00703 (2021)."},{"key":"e_1_3_2_2_7_1","volume-title":"Stochastic Intervention for Causal Effect Estimation. In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8.","author":"Duong Tri Dung","year":"2021","unstructured":"Tri Dung Duong , Qian Li , and Guandong Xu . 2021 . Stochastic Intervention for Causal Effect Estimation. In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8. Tri Dung Duong, Qian Li, and Guandong Xu. 2021. Stochastic Intervention for Causal Effect Estimation. In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5797"},{"key":"e_1_3_2_2_9_1","volume-title":"S1","author":"Flaxman Seth","year":"2016","unstructured":"Seth Flaxman , Sharad Goel , and Justin M Rao . 2016. Filter bubbles, echo chambers, and online news consumption. Public opinion quarterly 80 , S1 ( 2016 ), 298--320. Seth Flaxman, Sharad Goel, and Justin M Rao. 2016. Filter bubbles, echo chambers, and online news consumption. Public opinion quarterly 80, S1 (2016), 298--320."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1994.8753425"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/0471722146"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219965"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939815"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474247"},{"key":"e_1_3_2_2_16_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. 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_2_17_1","volume-title":"Learning causal effects via weighted empirical risk minimization. Advances in neural information processing systems 33","author":"Jung Yonghan","year":"2020","unstructured":"Yonghan Jung , Jin Tian , and Elias Bareinboim . 2020. Learning causal effects via weighted empirical risk minimization. Advances in neural information processing systems 33 ( 2020 ). Yonghan Jung, Jin Tian, and Elias Bareinboim. 2020. Learning causal effects via weighted empirical risk minimization. Advances in neural information processing systems 33 (2020)."},{"key":"e_1_3_2_2_18_1","unstructured":"Aviral Kumar Justin Fu George Tucker and Sergey Levine. 2019. Stabilizing Off- Policy Q-Learning via Bootstrapping Error Reduction. arXiv:1906.00949 [cs.LG]  Aviral Kumar Justin Fu George Tucker and Sergey Levine. 2019. Stabilizing Off- Policy Q-Learning via Bootstrapping Error Reduction. arXiv:1906.00949 [cs.LG]"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 3916--3924","author":"Li Qian","year":"2021","unstructured":"Qian Li , Tri Dung Duong , Zhichao Wang , Shaowu Liu , Dingxian Wang , and Guandong Xu . 2021 . Causal-Aware Generative Imputation for Automated Under-writing . In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 3916--3924 . Qian Li, Tri Dung Duong, Zhichao Wang, Shaowu Liu, Dingxian Wang, and Guandong Xu. 2021. Causal-Aware Generative Imputation for Automated Under-writing. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 3916--3924."},{"key":"e_1_3_2_2_20_1","volume-title":"Be Causal: De-biasing Social Network Confounding in Recommendation. arXiv preprint arXiv:2105.07775","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). 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_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3118542"},{"key":"e_1_3_2_2_22_1","volume-title":"Deep Treatment-Adaptive Network for Causal Inference. arXiv preprint arXiv:2112.13502","author":"Li Qian","year":"2021","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 ). 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_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"e_1_3_2_2_24_1","volume-title":"International Conference on Machine Learning. PMLR, 4055--4064","author":"Parmar Niki","year":"2018","unstructured":"Niki Parmar , Ashish Vaswani , Jakob Uszkoreit , Lukasz Kaiser , Noam Shazeer , Alexander Ku , and Dustin Tran . 2018 . Image transformer . In International Conference on Machine Learning. PMLR, 4055--4064 . Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Noam Shazeer, Alexander Ku, and Dustin Tran. 2018. Image transformer. In International Conference on Machine Learning. PMLR, 4055--4064."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3473320"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341161.3342859"},{"key":"e_1_3_2_2_27_1","first-page":"3","article-title":"The Optimizers Curse","volume":"52","author":"Smith James E.","year":"2006","unstructured":"James E. Smith and Robert L. Winkler . 2006 . The Optimizers Curse : Skepticism and Postdecision Surprise in Decision Analysis. Manage. Sci. 52 , 3 (mar 2006), 311--322. https:\/\/doi.org\/10.1287\/mnsc.1050.0451 10.1287\/mnsc.1050.0451 James E. Smith and Robert L. Winkler. 2006. The Optimizers Curse: Skepticism and Postdecision Surprise in Decision Analysis. Manage. Sci. 52, 3 (mar 2006), 311--322. https:\/\/doi.org\/10.1287\/mnsc.1050.0451","journal-title":"Skepticism and Postdecision Surprise in Decision Analysis. Manage. Sci."},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning. PMLR, 814--823","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--823 . Adith Swaminathan and Thorsten Joachims. 2015. Counterfactual risk minimization: Learning from logged bandit feedback. In International Conference on Machine Learning. PMLR, 814--823."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_2"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3159802"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_14"},{"key":"e_1_3_2_2_33_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams . 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3 ( 1992 ), 229--256. Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3 (1992), 229--256."},{"volume-title":"Wilcoxon Signed-Rank Test","author":"Woolson R. F.","key":"e_1_3_2_2_34_1","unstructured":"R. F. Woolson . 2008. Wilcoxon Signed-Rank Test . John Wiley & Sons, Ltd , 1--3. https:\/\/doi.org\/10.1002\/9780471462422.eoct979 arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/9780471462422.eoct979 10.1002\/9780471462422.eoct979 R. F. Woolson. 2008. Wilcoxon Signed-Rank Test. John Wiley & Sons, Ltd, 1--3. https:\/\/doi.org\/10.1002\/9780471462422.eoct979 arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/9780471462422.eoct979"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106524"},{"key":"e_1_3_2_2_36_1","volume-title":"Qian Li, Shaowu Liu, and Xianzhi Wang.","author":"Xu Guandong","year":"2020","unstructured":"Guandong Xu , Tri Dung Duong , Qian Li, Shaowu Liu, and Xianzhi Wang. 2020 . Causality learning: a new perspective for interpretable machine learning. arXiv preprint arXiv:2006.16789 (2020). Guandong Xu, Tri Dung 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_2_37_1","volume-title":"International Conference on Machine Learning. PMLR, 5453--5462","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu , Chengtao Li , Yonglong Tian , Tomohiro Sonobe , Ken-ichi Kawarabayashi, and Stefanie Jegelka . 2018 . Representation learning on graphs with jumping knowledge networks . In International Conference on Machine Learning. PMLR, 5453--5462 . Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. In International Conference on Machine Learning. PMLR, 5453--5462."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-019-01691-w"},{"key":"e_1_3_2_2_39_1","volume-title":"Heterogeneous Information Assisted Bandit Learning: Theory and Application. In 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 2135--2140","author":"Zhang Xiaoying","year":"2021","unstructured":"Xiaoying Zhang , Hong Xie , and John CS Lui . 2021 . Heterogeneous Information Assisted Bandit Learning: Theory and Application. In 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 2135--2140 . Xiaoying Zhang, Hong Xie, and John CS Lui. 2021. Heterogeneous Information Assisted Bandit Learning: Theory and Application. In 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 2135--2140."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098063"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401174"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Madrid Spain","acronym":"SIGIR '22"},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3532021","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3532021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:21Z","timestamp":1750183821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3532021"}},"subtitle":["Meta Graph Enhanced Off-policy Learning for Recommendations"],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":43,"alternative-id":["10.1145\/3477495.3532021","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3532021","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}