{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T15:32:08Z","timestamp":1771342328724,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T00:00:00Z","timestamp":1595635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["91646202"],"award-info":[{"award-number":["91646202"]}]},{"name":"National Key R&D Program of China","award":["2018YFB1404401"],"award-info":[{"award-number":["2018YFB1404401"]}]},{"name":"National Key R&D Program of China","award":["2018YFB1402701"],"award-info":[{"award-number":["2018YFB1402701"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,25]]},"DOI":"10.1145\/3397271.3401171","type":"proceedings-article","created":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T07:50:08Z","timestamp":1595663408000},"page":"239-248","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":98,"title":["Leveraging Demonstrations for Reinforcement Recommendation Reasoning over Knowledge Graphs"],"prefix":"10.1145","author":[{"given":"Kangzhi","family":"Zhao","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiting","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuren","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxiao","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,7,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/a11090137"},{"key":"e_1_3_2_1_2_1","unstructured":"Dzmitry Bahdanau Philemon Brakel Kelvin Xu Anirudh Goyal Ryan Lowe Joelle Pineau Aaron C. Courville and Yoshua Bengio. 2017. An Actor-Critic Algorithm for Sequence Prediction. In ICLR (Poster).  Dzmitry Bahdanau Philemon Brakel Kelvin Xu Anirudh Goyal Ryan Lowe Joelle Pineau Aaron C. Courville and Yoshua Bengio. 2017. An Actor-Critic Algorithm for Sequence Prediction. In ICLR (Poster)."},{"key":"e_1_3_2_1_3_1","volume-title":"Dynamic Programming","author":"Bellman R","year":"2013","unstructured":"R Bellman . 2013. Dynamic Programming , Courier Corporation . New York, NY, Vol. 707 ( 2013 ). R Bellman. 2013. Dynamic Programming, Courier Corporation. New York, NY, Vol. 707 (2013)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/937503.937505"},{"key":"e_1_3_2_1_5_1","volume-title":"Jason Weston, and Oksana Yakhnenko.","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes , Nicolas Usunier , Alberto Garc'i a-Dur\u00e1 n , Jason Weston, and Oksana Yakhnenko. 2013 . Translating Embeddings for Modeling Multi-relational Data. In NIPS. 2787--2795. Antoine Bordes, Nicolas Usunier, Alberto Garc'i a-Dur\u00e1 n, Jason Weston, and Oksana Yakhnenko. 2013. Translating Embeddings for Modeling Multi-relational Data. In NIPS. 2787--2795."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Yixin Cao Xiang Wang Xiangnan He Zikun Hu and Tat-Seng Chua. 2019. Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences. In WWW. ACM 151--161.  Yixin Cao Xiang Wang Xiangnan He Zikun Hu and Tat-Seng Chua. 2019. Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences. In WWW. ACM 151--161.","DOI":"10.1145\/3308558.3313705"},{"key":"e_1_3_2_1_7_1","volume-title":"Cohen","author":"Catherine Rose","year":"2016","unstructured":"Rose Catherine and William W . Cohen . 2016 . Personalized Recommendations using Knowledge Graphs : A Probabilistic Logic Programming Approach. In RecSys. ACM , 325--332. Rose Catherine and William W. Cohen. 2016. Personalized Recommendations using Knowledge Graphs: A Probabilistic Logic Programming Approach. In RecSys. ACM, 325--332."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Shi-Yong Chen Yang Yu Qing Da Jun Tan Hai-Kuan Huang and Hai-Hong Tang. 2018. Stabilizing Reinforcement Learning in Dynamic Environment with Application to Online Recommendation. In KDD. ACM 1187--1196.  Shi-Yong Chen Yang Yu Qing Da Jun Tan Hai-Kuan Huang and Hai-Hong Tang. 2018. Stabilizing Reinforcement Learning in Dynamic Environment with Application to Online Recommendation. In KDD. ACM 1187--1196.","DOI":"10.1145\/3219819.3220122"},{"key":"e_1_3_2_1_9_1","unstructured":"Xinshi Chen Shuang Li Hui Li Shaohua Jiang Yuan Qi and Le Song. 2019 a. Generative Adversarial User Model for Reinforcement Learning Based Recommendation System. In ICML. PMLR 1052--1061.  Xinshi Chen Shuang Li Hui Li Shaohua Jiang Yuan Qi and Le Song. 2019 a. Generative Adversarial User Model for Reinforcement Learning Based Recommendation System. In ICML. PMLR 1052--1061."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Zhongxia Chen Xiting Wang Xing Xie Mehul Parsana Akshay Soni Xiang Ao and Enhong Chen. 2020. Towards Explainable Conversational Recommendation. In IJCAI.  Zhongxia Chen Xiting Wang Xing Xie Mehul Parsana Akshay Soni Xiang Ao and Enhong Chen. 2020. Towards Explainable Conversational Recommendation. In IJCAI.","DOI":"10.24963\/ijcai.2020\/414"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Zhongxia Chen Xiting Wang Xing Xie Tong Wu Guoqing Bu Yining Wang and Enhong Chen. 2019 b. Co-attentive multi-task learning for explainable recommendation. In IJCAI. 2137--2143.  Zhongxia Chen Xiting Wang Xing Xie Tong Wu Guoqing Bu Yining Wang and Enhong Chen. 2019 b. Co-attentive multi-task learning for explainable recommendation. In IJCAI. 2137--2143.","DOI":"10.24963\/ijcai.2019\/296"},{"key":"e_1_3_2_1_12_1","volume-title":"mbox","author":"Dijkstra Edsger W","year":"1959","unstructured":"Edsger W Dijkstra mbox . 1959 . A note on two problems in connexion with graphs. Numerische mathematik, Vol. 1 , 1 (1959), 269--271. Edsger W Dijkstra et almbox. 1959. A note on two problems in connexion with graphs. Numerische mathematik, Vol. 1, 1 (1959), 269--271."},{"key":"e_1_3_2_1_13_1","unstructured":"Shaohua Fan Junxiong Zhu Xiaotian Han Chuan Shi Linmei Hu Biyu Ma and Yongliang Li. 2019. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation. In KDD. ACM 2478--2486.  Shaohua Fan Junxiong Zhu Xiaotian Han Chuan Shi Linmei Hu Biyu Ma and Yongliang Li. 2019. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation. In KDD. ACM 2478--2486."},{"key":"e_1_3_2_1_14_1","unstructured":"Jingyue Gao Xiting Wang Yasha Wang and Xing Xie. 2019. Explainable Recommendation Through Attentive Multi-View Learning. AAAI.  Jingyue Gao Xiting Wang Yasha Wang and Xing Xie. 2019. Explainable Recommendation Through Attentive Multi-View Learning. AAAI."},{"key":"e_1_3_2_1_15_1","first-page":"280","article-title":"Crowd sourcing information to fulfill user requests","volume":"9","author":"Gruber Thomas R","year":"2016","unstructured":"Thomas R Gruber , Adam J Cheyer , and Donald W Pitschel . 2016 . Crowd sourcing information to fulfill user requests . US Patent 9 , 280 ,610. Thomas R Gruber, Adam J Cheyer, and Donald W Pitschel. 2016. Crowd sourcing information to fulfill user requests. US Patent 9,280,610.","journal-title":"US Patent"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Tao Gui Peng Liu Qi Zhang Liang Zhu Minlong Peng Yunhua Zhou and Xuanjing Huang. 2019. Mention Recommendation in Twitter with Cooperative Multi-Agent Reinforcement Learning. In SIGIR. ACM 535--544.  Tao Gui Peng Liu Qi Zhang Liang Zhu Minlong Peng Yunhua Zhou and Xuanjing Huang. 2019. Mention Recommendation in Twitter with Cooperative Multi-Agent Reinforcement Learning. In SIGIR. ACM 535--544.","DOI":"10.1145\/3331184.3331237"},{"key":"e_1_3_2_1_17_1","volume-title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","author":"He Kaiming","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2015. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification . In ICCV. IEEE Computer Society , 1026--1034. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In ICCV. IEEE Computer Society, 1026--1034."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/358916.358995"},{"key":"e_1_3_2_1_19_1","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. In NIPS. 4565--4573.  Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. In NIPS. 4565--4573."},{"key":"e_1_3_2_1_20_1","volume-title":"Wayne Xin Zhao, and Philip S. Yu","author":"Hu Binbin","year":"2018","unstructured":"Binbin Hu , Chuan Shi , Wayne Xin Zhao, and Philip S. Yu . 2018 . Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model. In KDD. ACM , 1531--1540. Binbin Hu, Chuan Shi, Wayne Xin Zhao, and Philip S. Yu. 2018. Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model. In KDD. ACM, 1531--1540."},{"key":"e_1_3_2_1_21_1","volume-title":"Hong-Jian Dou, Ji-Rong Wen, and Edward Y. Chang.","author":"Huang Jin","year":"2018","unstructured":"Jin Huang , Wayne Xin Zhao , Hong-Jian Dou, Ji-Rong Wen, and Edward Y. Chang. 2018 . Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks. In SIGIR. ACM , 505--514. Jin Huang, Wayne Xin Zhao, Hong-Jian Dou, Ji-Rong Wen, and Edward Y. Chang. 2018. Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks. In SIGIR. ACM, 505--514."},{"key":"e_1_3_2_1_22_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba . 2015 . Adam : A Method for Stochastic Optimization. In ICLR (Poster) . Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR (Poster)."},{"key":"e_1_3_2_1_23_1","volume-title":"Rationalizing neural predictions. arXiv preprint arXiv:1606.04155","author":"Lei Tao","year":"2016","unstructured":"Tao Lei , Regina Barzilay , and Tommi Jaakkola . 2016. Rationalizing neural predictions. arXiv preprint arXiv:1606.04155 ( 2016 ). Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2016. Rationalizing neural predictions. arXiv preprint arXiv:1606.04155 (2016)."},{"key":"e_1_3_2_1_24_1","unstructured":"Piji Li Zihao Wang Zhaochun Ren Lidong Bing and Wai Lam. 2017. Neural rating regression with abstractive tips generation for recommendation. In SIGIR. 345--354.  Piji Li Zihao Wang Zhaochun Ren Lidong Bing and Wai Lam. 2017. Neural rating regression with abstractive tips generation for recommendation. In SIGIR. 345--354."},{"key":"e_1_3_2_1_25_1","unstructured":"Timothy P. Lillicrap Jonathan J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2016. Continuous control with deep reinforcement learning. In ICLR (Poster).  Timothy P. Lillicrap Jonathan J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2016. Continuous control with deep reinforcement learning. In ICLR (Poster)."},{"key":"e_1_3_2_1_26_1","volume-title":"mbox","author":"L\u00e1szl\u00f3 Lov\u00e1sz","year":"1993","unstructured":"L\u00e1szl\u00f3 Lov\u00e1sz et al mbox . 1993 . Random walks on graphs: A survey. Combinatorics, Paul erdos is eighty, Vol. 2 , 1 (1993), 1--46. L\u00e1szl\u00f3 Lov\u00e1sz et almbox. 1993. Random walks on graphs: A survey. Combinatorics, Paul erdos is eighty, Vol. 2, 1 (1993), 1--46."},{"key":"e_1_3_2_1_27_1","unstructured":"Weizhi Ma Min Zhang Yue Cao Woojeong Jin Chenyang Wang Yiqun Liu Shaoping Ma and Xiang Ren. 2019. Jointly Learning Explainable Rules for Recommendation with Knowledge Graph. In WWW. ACM 1210--1221.  Weizhi Ma Min Zhang Yue Cao Woojeong Jin Chenyang Wang Yiqun Liu Shaoping Ma and Xiang Ren. 2019. Jointly Learning Explainable Rules for Recommendation with Knowledge Graph. In WWW. ACM 1210--1221."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Enrico Palumbo Giuseppe Rizzo and Rapha\u00eb l Troncy. 2017. entity2rec: Learning User-Item Relatedness from Knowledge Graphs for Top-N Item Recommendation. In RecSys. ACM 32--36.  Enrico Palumbo Giuseppe Rizzo and Rapha\u00eb l Troncy. 2017. entity2rec: Learning User-Item Relatedness from Knowledge Graphs for Top-N Item Recommendation. In RecSys. ACM 32--36.","DOI":"10.1145\/3109859.3109889"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"e_1_3_2_1_30_1","volume-title":"BPR: Bayesian Personalized Ranking from Implicit Feedback","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle , Christoph Freudenthaler , Zeno Gantner , and Lars Schmidt-Thieme . 2009 . BPR: Bayesian Personalized Ranking from Implicit Feedback . In UAI. AUAI Press , 452--461. Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian Personalized Ranking from Implicit Feedback. In UAI. AUAI Press, 452--461."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Wenjie Shang Yang Yu Qingyang Li Zhiwei Qin Yiping Meng and Jieping Ye. 2019. Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation. In KDD. ACM 566--576.  Wenjie Shang Yang Yu Qingyang Li Zhiwei Qin Yiping Meng and Jieping Ye. 2019. Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation. In KDD. ACM 566--576.","DOI":"10.1145\/3292500.3330933"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1088715"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Amit Sharma and Dan Cosley. 2013. Do social explanations work?: studying and modeling the effects of social explanations in recommender systems. In WWW. ACM 1133--1144.  Amit Sharma and Dan Cosley. 2013. Do social explanations work?: studying and modeling the effects of social explanations in recommender systems. In WWW. ACM 1133--1144.","DOI":"10.1145\/2488388.2488487"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2481244.2481248"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Zhu Sun Jie Yang Jie Zhang Alessandro Bozzon Long-Kai Huang and Chi Xu. 2018. Recurrent knowledge graph embedding for effective recommendation. In RecSys. ACM 297--305.  Zhu Sun Jie Yang Jie Zhang Alessandro Bozzon Long-Kai Huang and Chi Xu. 2018. Recurrent knowledge graph embedding for effective recommendation. In RecSys. ACM 297--305.","DOI":"10.1145\/3240323.3240361"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"e_1_3_2_1_37_1","volume-title":"Barto","author":"Sutton Richard S.","year":"1998","unstructured":"Richard S. Sutton and Andrew G . Barto . 1998 . Reinforcement learning - an introduction. MIT Press . Richard S. Sutton and Andrew G. Barto. 1998. Reinforcement learning - an introduction. MIT Press."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2007.4401070"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Hongwei Wang Fuzheng Zhang Jialin Wang Miao Zhao Wenjie Li Xing Xie and Minyi Guo. 2018c. RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems. In CIKM. ACM 417--426.  Hongwei Wang Fuzheng Zhang Jialin Wang Miao Zhao Wenjie Li Xing Xie and Minyi Guo. 2018c. RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems. In CIKM. ACM 417--426.","DOI":"10.1145\/3269206.3271739"},{"key":"e_1_3_2_1_40_1","volume-title":"DKN: Deep Knowledge-Aware Network for News Recommendation. In WWW. ACM","author":"Wang Hongwei","year":"2018","unstructured":"Hongwei Wang , Fuzheng Zhang , Xing Xie , and Minyi Guo . 2018 d . DKN: Deep Knowledge-Aware Network for News Recommendation. In WWW. ACM , 1835--1844. Hongwei Wang, Fuzheng Zhang, Xing Xie, and Minyi Guo. 2018 d. DKN: Deep Knowledge-Aware Network for News Recommendation. In WWW. ACM, 1835--1844."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Lu Wang Wei Zhang Xiaofeng He and Hongyuan Zha. 2018b. Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation. In KDD. ACM 2447--2456.  Lu Wang Wei Zhang Xiaofeng He and Hongyuan Zha. 2018b. Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation. In KDD. ACM 2447--2456.","DOI":"10.1145\/3219819.3219961"},{"key":"e_1_3_2_1_42_1","volume-title":"A Reinforcement Learning Framework for Explainable Recommendation","author":"Wang Xiting","unstructured":"Xiting Wang , Yiru Chen , Jie Yang , Le Wu , Zhengtao Wu , and Xing Xie . 2018a. A Reinforcement Learning Framework for Explainable Recommendation . In ICDM. IEEE , 587--596. Xiting Wang, Yiru Chen, Jie Yang, Le Wu, Zhengtao Wu, and Xing Xie. 2018a. A Reinforcement Learning Framework for Explainable Recommendation. In ICDM. IEEE, 587--596."},{"key":"e_1_3_2_1_43_1","volume-title":"Explainable Reasoning over Knowledge Graphs for Recommendation","author":"Wang Xiang","unstructured":"Xiang Wang , Dingxian Wang , Canran Xu , Xiangnan He , Yixin Cao , and Tat-Seng Chua . 2019. Explainable Reasoning over Knowledge Graphs for Recommendation . In AAAI. AAAI Press , 5329--5336. Xiang Wang, Dingxian Wang, Canran Xu, Xiangnan He, Yixin Cao, and Tat-Seng Chua. 2019. Explainable Reasoning over Knowledge Graphs for Recommendation. In AAAI. AAAI Press, 5329--5336."},{"key":"e_1_3_2_1_44_1","volume-title":"Knowledge Graph Embedding by Translating on Hyperplanes","author":"Wang Zhen","unstructured":"Zhen Wang , Jianwen Zhang , Jianlin Feng , and Zheng Chen . 2014. Knowledge Graph Embedding by Translating on Hyperplanes . In AAAI. AAAI Press , 1112--1119. Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014. Knowledge Graph Embedding by Translating on Hyperplanes. In AAAI. AAAI Press, 1112--1119."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Yikun Xian Zuohui Fu S. Muthukrishnan Gerard de Melo and Yongfeng Zhang. 2019. Reinforcement Knowledge Graph Reasoning for Explainable Recommendation. In SIGIR. ACM 285--294.  Yikun Xian Zuohui Fu S. Muthukrishnan Gerard de Melo and Yongfeng Zhang. 2019. Reinforcement Knowledge Graph Reasoning for Explainable Recommendation. In SIGIR. ACM 285--294.","DOI":"10.1145\/3331184.3331203"},{"key":"e_1_3_2_1_47_1","volume-title":"Deeppath: A reinforcement learning method for knowledge graph reasoning. In EMNLP.","author":"Xiong Wenhan","year":"2017","unstructured":"Wenhan Xiong , Thien Hoang , and William Yang Wang . 2017 . Deeppath: A reinforcement learning method for knowledge graph reasoning. In EMNLP. Wenhan Xiong, Thien Hoang, and William Yang Wang. 2017. Deeppath: A reinforcement learning method for knowledge graph reasoning. In EMNLP."},{"key":"e_1_3_2_1_48_1","unstructured":"Xiao Yu Xiang Ren Yizhou Sun Quanquan Gu Bradley Sturt Urvashi Khandelwal Brandon Norick and Jiawei Han. 2014. Personalized entity recommendation: a heterogeneous information network approach. In WSDM. ACM 283--292.  Xiao Yu Xiang Ren Yizhou Sun Quanquan Gu Bradley Sturt Urvashi Khandelwal Brandon Norick and Jiawei Han. 2014. Personalized entity recommendation: a heterogeneous information network approach. In WSDM. ACM 283--292."},{"key":"e_1_3_2_1_49_1","volume-title":"Defu Lian, Xing Xie, and Wei-Ying Ma.","author":"Zhang Fuzheng","year":"2016","unstructured":"Fuzheng Zhang , Nicholas Jing Yuan , Defu Lian, Xing Xie, and Wei-Ying Ma. 2016 . Collaborative Knowledge Base Embedding for Recommender Systems. In KDD. ACM , 353--362. Fuzheng Zhang, Nicholas Jing Yuan, Defu Lian, Xing Xie, and Wei-Ying Ma. 2016. Collaborative Knowledge Base Embedding for Recommender Systems. In KDD. ACM, 353--362."},{"key":"e_1_3_2_1_50_1","volume-title":"Hierarchical Reinforcement Learning for Course Recommendation in MOOCs","author":"Zhang Jing","unstructured":"Jing Zhang , Bowen Hao , Bo Chen , Cuiping Li , Hong Chen , and Jimeng Sun . 2019. Hierarchical Reinforcement Learning for Course Recommendation in MOOCs . In AAAI. AAAI Press , 435--442. Jing Zhang, Bowen Hao, Bo Chen, Cuiping Li, Hong Chen, and Jimeng Sun. 2019. Hierarchical Reinforcement Learning for Course Recommendation in MOOCs. In AAAI. AAAI Press, 435--442."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Yongfeng Zhang Qingyao Ai Xu Chen and W. Bruce Croft. 2017. Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources. In CIKM. ACM 1449--1458.  Yongfeng Zhang Qingyao Ai Xu Chen and W. Bruce Croft. 2017. Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources. In CIKM. ACM 1449--1458.","DOI":"10.1145\/3132847.3132892"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Yongfeng Zhang Guokun Lai Min Zhang Yi Zhang Yiqun Liu and Shaoping Ma. 2014. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In SIGIR. 83--92.  Yongfeng Zhang Guokun Lai Min Zhang Yi Zhang Yiqun Liu and Shaoping Ma. 2014. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In SIGIR. 83--92.","DOI":"10.1145\/2600428.2609579"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Huan Zhao Quanming Yao Jianda Li Yangqiu Song and Dik Lun Lee. 2017. Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks. In KDD. ACM 635--644.  Huan Zhao Quanming Yao Jianda Li Yangqiu Song and Dik Lun Lee. 2017. Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks. In KDD. ACM 635--644.","DOI":"10.1145\/3097983.3098063"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Long Xia Liang Zhang Zhuoye Ding Dawei Yin and Jiliang Tang. 2018a. Deep reinforcement learning for page-wise recommendations. In RecSys. ACM 95--103.  Xiangyu Zhao Long Xia Liang Zhang Zhuoye Ding Dawei Yin and Jiliang Tang. 2018a. Deep reinforcement learning for page-wise recommendations. In RecSys. ACM 95--103.","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Liang Zhang Zhuoye Ding Long Xia Jiliang Tang and Dawei Yin. 2018b. Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning. In KDD. ACM 1040--1048.  Xiangyu Zhao Liang Zhang Zhuoye Ding Long Xia Jiliang Tang and Dawei Yin. 2018b. Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning. In KDD. ACM 1040--1048.","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_56_1","volume-title":"Xing Xie, and Zhenhui Li.","author":"Zheng Guanjie","year":"2018","unstructured":"Guanjie Zheng , Fuzheng Zhang , Zihan Zheng , Yang Xiang , Nicholas Jing Yuan , Xing Xie, and Zhenhui Li. 2018 . DRN : A Deep Reinforcement Learning Framework for News Recommendation. In WWW. ACM , 167--176. Guanjie Zheng, Fuzheng Zhang, Zihan Zheng, Yang Xiang, Nicholas Jing Yuan, Xing Xie, and Zhenhui Li. 2018. DRN: A Deep Reinforcement Learning Framework for News Recommendation. In WWW. ACM, 167--176."}],"event":{"name":"SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval","location":"Virtual Event China","acronym":"SIGIR '20","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401171","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397271.3401171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:43Z","timestamp":1750200103000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,25]]},"references-count":56,"alternative-id":["10.1145\/3397271.3401171","10.1145\/3397271"],"URL":"https:\/\/doi.org\/10.1145\/3397271.3401171","relation":{},"subject":[],"published":{"date-parts":[[2020,7,25]]},"assertion":[{"value":"2020-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}