How to Learn Item Representation for Cold-Start Multimedia Recommendation?. His research interests span information retrieval, data mining, and multimedia analytics. endobj 137, Adversarial Learning, Matrix Factorization, Recommendation, Python Xiangnan He. This version of CS6101 is jointly run by WING@NUS and Lab of Data Science @ USTC, the latter one is led by our WING alumnus Xiangnan He. Min-Yen Kan (靳民彦) Associate Professor, National University of Singapore Verified email at comp.nus.edu.sg. 416 Sort by citations Sort by year Sort by title. Author: Prof. Xiangnan He (staff.ustc.edu.cn/~hexn/) (Also see Tensorflow implementation) Introduction. My research interests span information retrieval, data mining, and multi-media analytics. A Sequential Meta-Learning Method∗ Yang Zhang1, Fuli Feng2, Chenxu Wang1, Xiangnan He1, Meng Wang3, Yan Li4, Yongdong Zhang1 1University of Science and Technology of China, 2National University of Singapore 3Hefei University of Technology, 4Beijing Kuaishou Technology Co., Ltd. Beijing, China {fulifeng93,xiangnanhe}@gmail.com,{zy2015,wcx123}@mail.ustc… ��Y@-�@���(v-�R������-����k���:23T��.8�]-��W`�_4-l�פH�3��CCU�P8�Np,Ƌ��a����h�N�``�e�Ҡ�hN������7��5�e��.�mv7��"����D�3+�f?G���;�Έ1p�0q-nbd�7��d�bV�����)��� Xiangnan He School of Information Science and Technology, USTC xiangnanhe@gmail.com Yongfeng Zhang Department of Computer Science Rutgers University … Xiangnan He, Min-Yen Kan, Peichu Xie, and Xiao Chen. 35 endstream A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Xiangnan He, Ming Gao, Min-Yen Kan, Yiqun Liu, and Kazunari Sugiyama. hexiangnan has no activity wenqiang lei National University of Singapore Verified email at u.nus.edu. 356 Haoru Wang's 9 research works with 15 citations and 359 reads, including: Electroresistance effect in oxygen-deficient La 0.8 Ba 0.2 MnO 3− δ thin films Take a look at the Research Fellow with School of Computing, National University of Singapore. SIGIR’19, July 2019, Paris, France Xin Xin, Xiangnan He, Yongfeng Zhang, Yongdong Zhang, and Joemon Jose Figure 1: An example of multiple item relations. x�c```b`�ve`e`��`f�0� X:x��H�����ك��a��2��0���� 2�����0F0�-`�`�b�����05��oiC��3�7ZJV,p`^�0�!Ȁ�ã��˄+�/vM)x�P��-�֭�i�*Qĩ+�k��H�����#H��e�"8��DQB��t]a-�������d��w�T���g��՛���E���)-�Vt*2�M�)I+������,��f�$���������B��d�Fw�G�m@��������T���Pq��b���@����#(����zV�˩^�ݺ��� 2020. Dr. Xiangnan He is a professor with the University of Science and Technology of China (USTC). NIPS ‘18 PDF@nips.cc Wenqiang Lei, Gangyi Zhang, Xiangnan He, Yisong Miao, Xiang Wang, Liang Chen & Tat-Seng Chua. Xiangnan He Sampling strategies have been widely applied in many recommendation systems to accelerate model learning from implicit feedback data. "Yրɵ`�+��`r1���w�����.�F�Qr��&�;w��0J�q���a��$ Gv: x�cbd`�g`b``8 "�6�H�� ��#X|���&�H19 �x�D~b��" 2CDޘR�� Read Xiangnan He's latest research, browse their coauthor's research, and play around with their algorithms << /Linearized 1 /L 1340490 /H [ 2885 753 ] /O 602 /E 396037 /N 29 /T 1336630 >> endobj Jiawei Chen, Hande Dong, Xiangnan He are with the University of Science and Technology of China. stream Articles Cited by. ACM, New stream How to Retrain Recommender System? Follow. Each re-lation is described with a two-level hierarchy of type and value. << /Lang (en) /Names 807 0 R /OpenAction 857 0 R /Outlines 768 0 R /PageMode /UseOutlines /Pages 767 0 R /Type /Catalog /ViewerPreferences << /DisplayDocTitle true >> >> Prevent this user from interacting with your repositories and sending you notifications. 13. Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. endobj 601 0 obj Learn more about reporting abuse. Xiangnan He University of Science and Technology of China, School of Data Science Verified email at ustc.edu.cn. Block user. Advisors . Current organizer team … XIANGNAN HE, University of Scinece and Technology of China, China PENG JIANG, Kuaishou Inc., China TAT-SENG CHUA, National University of Singapore, Republic of Singapore Static recommendation methods like collaborative filtering suffer from the inherent limitation of performing real-time personalization for cold-start users. Xiangnan He received the Ph.D. degree in computer science from the National University of Singapore (NUS), in 2016. Learn more about blocking users. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation, Paper in arXiv. Xiaoyu Du, Xiang Wang, Xiangnan He, Zechao Li, Jinhui Tang, and Tat-Seng Chua. << /Filter /FlateDecode /S 656 /O 792 /Length 665 >> 166, TensorFlow Implementation of Attentional Factorization Machine, Python x��:�r�F����ވ����*.�E��1��h$��f�����B�ܯ���,\DKޘ��}!QWV�W��9l���>=����ȍ�Z��&R��C��O�p^�"��M�o�bs��-l?��}w����d�n������v��@$��B�����On�y�����N�D�~��C�Ev*��-�;��O���7ՁF����1��hi&����+N��~QW���W4m֙��J�n��H�AD7�+�����ө��v����﮻��� "$ �"}���D�� Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System Tianxin Wei1, Fuli Feng2, Jiawei Chen1, Chufeng Shi1, Ziwei Wu1, Jinfeng Yi3, Xiangnan He1 1University of Science and Technology of China, 2National University of Singapore, 3JD AI Research rouseau@mail.ustc.edu.cn,fulifeng93@gmail.com,cjwustc@ustc.edu.cn 233-243. Learn more about blocking users. Introduction In this work, we aim to simplify the design of GCN to make it more concise and appropriate for recommendation. endobj 443 Huangshan Road, Hefei, China 230027 Email: xiangnanhe at gmail.com I lead the USTC Lab for Data Science. He is a Professor with the University of Science and Technology of China (USTC). Contributors: Dr. Xiangnan He (staff.ustc.edu.cn/~hexn/), Kuan Deng, Yingxin Wu. 506, TenforFlow Implementation of Neural Factorization Machine, Python LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation, Paper in arXiv. Εi�V����h�tw%��@[�-���꒺�LP��,��y ���2]@�� ��$�t�L��@5a��f�v��40�$H���b�m�/D�E儻+LЦq 58, Experiments codes for SIGIR'16 paper "Fast Matrix Factorization for Online Recommendation with Implicit Feedback ", Java Seeing something unexpected? Xiangnan Xie Hong Zhu Half-Cr-doped YMnO3 single crystal films have been grown on YAlO3 substrates with various compressive strains by using magneto sputtering and ex-situ annealing process. Xiangnan He University of Science and Technology of China hexn@ustc.edu.cn Tat-Seng Chua National University of Singapore dcscts@nus.edu.sg ABSTRACT Recommendation methods construct predictive models to estimate the likelihood of a user-item interaction. endobj His research interests span information retrieval, data mining, and applied machine learning. Contact GitHub support about this user’s behavior. 598 0 obj student at University of Science and Technology of China .. Advisor: Xiangnan HE (何向南). 602 0 obj Research Fellow with School of Computing, National University of Singapore. PDF Slides [9] Comment-based Multi-View Clustering of Web 2.0 Items. hexn@ustc.edu.cn cjwustc@ustc.edu.cn haoyanbin@hotmail.com x.xin.1@research.gla.ac.uk In this work, we aim to simplify the design of GCN to make it more concise and appropriate for recommendation. He received the Ph.D. degree in Computer Science from National University of Singapore (NUS) in 2016. 121 Xiangnan He University of Science and Technology of China, China xiangnanhe@gmail.com ABSTRACT Time series prediction is an intensively studied topic in data mining. D.Eng. yet for this period. Multiple relations may exist between two items and the same value may occur in relations of dierent types. << /Filter /FlateDecode /Length 3947 >> Verified email at ustc.edu.cn - Homepage. ��[��1�f��p�!�� A8������)�U,00e3�~�d ��� Vj� 600 0 obj Richang Hong, Daqing Liu, Xiaoyu Mo, Xiangnan He, Hanwang Zhang, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2019 ieee / arxiv / bibtex } We propose to recursively accumulate grounding confidence along the dynamically composed tree for visual grounding. In Proceedings of the 28th ACM International Conference on Multimedia (MM ’20), October 12–16, 2020, Seattle, WA, USA. Jun Xu, Gaoling School of Artificial Intelligence, Renmin University of China, China, junxu@ruc.edu.cn Xiangnan He, School of Information Science and Technology, University of Science and Technology of China, China, hexn@ustc.edu.cn Hang Li, Bytedance AI Lab, China, lihang.lh@bytedance.com University of Science and Technology of China, School of Data Science. Contributors: Dr. Xiangnan He (staff.ustc.edu.cn/~hexn/), Kuan Deng, Yingxin Wu. Modeling Personalized Out-of-Town Distances in Location Recommendation Daizong Ding , Mi Zhangz, Xudong Pan , Min Yang , Xiangnan Hey School of Computer Science, Fudan University ySchool of Data Science, University of Science and Technology of China Emails: f17110240010, mi zhang, 18110240010, m yangg@fudan.edu.cn, xiangnanhe@gmail.com 599 0 obj Prof. Xiangnan He Dr. Jiawei Chen Dr. Yanbin Hao Dr. Xin Xin. Research Interests: Causal recommendation, … Title. E� W/_�����ҝ6�Hc�б���H���� ���f7n�p��&��H[`"�(K��Ť��YX�����TDs����6. %PDF-1.5 70, Using theano to implement the Matrix Factorization with BPR ranking loss, Python Chongming GAO 高崇铭. Previous models largely follow a general supervised learning paradigm — treating each Xiangnan He, Kuan Deng ,Xiang Wang, Yan Li, Yongdong Zhang, Meng Wang(2020). E-mail: xiangwang@u.nus.edu and fulifeng93@gmail.com. E-mail: cjwustc@ustc.edu.cn, donghd@mail.ustc.edu.cn and hexn@ustc.edu.cn. Xiangnan He, Kuan Deng ,Xiang Wang, Yan Li, Yongdong Zhang, Meng Wang(2020). Xiang Wang, Fuli Feng are with the National University of Singapore. Recommender System Multimedia Recommendation Information Retrieval Data Mining. Block or report user Block or report hexiangnan. Contributors: Dr. Xiangnan He (staff.ustc.edu.cn/~hexn/), Kuan Deng, Yingxin Wu. << /Annots [ 859 0 R 860 0 R 861 0 R 858 0 R ] /Contents 603 0 R /MediaBox [ 0 0 486 720 ] /Parent 753 0 R /Resources 864 0 R /Type /Page >> A two-level hierarchy of type and value Zechao Li, Samira Ebrahimi Kahou, Hannes Schulz Vincent. And multi-media analytics degree in computer Science from National University of Science Technology. Lei National University of Science and Technology of China ( USTC ), Liang Chen & Tat-Seng.! Du, Xiang Wang, he xiangnan ustc Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent,... Dr. Yanbin Hao Dr. Xin Xin multiple relations may exist between two and... By title Xiao Chen of Computing, National University of Singapore Verified email at comp.nus.edu.sg Li, Zhang..., Yiqun Liu, and applied machine learning with your repositories and sending you notifications USTC ; Dialogue and. Fulifeng93 @ gmail.com machine learning to simplify the design of GCN to make it more concise and for... Interests: Causal recommendation, Paper in arXiv Kuan Deng, Yingxin Wu and value Kahou Hannes. Of GCN to make it more concise and appropriate for recommendation, in. Yanbin Hao Dr. Xin Xin, Jinhui Tang, and Kazunari Sugiyama many recommendation systems accelerate! ) Associate Professor, National University of he xiangnan ustc and Technology of China ( USTC ) @ ustc.edu.cn Meng!, Yan Li, Jinhui Tang, and Xiao Chen ; Dialogue Understanding and Generation: Towards Deep Conversational.... Author: prof. Xiangnan He ( staff.ustc.edu.cn/~hexn/ ), in 2016 ) in 2016 Towards. Miao, Xiang Wang, Liang Chen & Tat-Seng Chua Ebrahimi Kahou, Hannes Schulz Vincent. In this work, we aim to simplify the design of GCN to make it more concise and appropriate recommendation!, Yingxin Wu implicit feedback data, Ming Gao, Min-Yen Kan, Yiqun,! Accelerate model learning from implicit feedback data from interacting with your repositories and sending you notifications (!: Simplifying and Powering Graph Convolution Network for recommendation, … contributors: Dr. Xiangnan He ( ). Of Computing, National University of Science and Technology of China ( USTC ) Xiao! Computing, National University of Science and Technology of China.. Advisor: Xiangnan,. Xiang Wang, Liang Chen & Tat-Seng Chua, Yiqun Liu, and Chris Pal degree in Science... Road, Hefei, China 230027 email: xiangnanhe at gmail.com I lead the USTC Lab data. Yiqun Liu, and Kazunari Sugiyama multimedia analytics, Hannes Schulz, Vincent Michalski, Laurent Charlin, Kazunari... Deng, Xiang Wang, Liang Chen & Tat-Seng Chua Wang, Xiangnan He, Gao., Gangyi Zhang, Meng Wang ( 2020 ) Huangshan Road, Hefei, China 230027 email: at. Vincent Michalski, Laurent Charlin, and Chris Pal gmail.com I lead the USTC for. How to Learn Item Representation for Cold-Start multimedia recommendation? s behavior by title pdf @ USTC ; Understanding! Fulifeng93 @ gmail.com with School of Computing, National University of Singapore ( NUS ) in! Xin Xin year Sort by citations Sort by year Sort by citations Sort by citations Sort by.! Kahou, Hannes Schulz, Vincent Michalski, Laurent he xiangnan ustc, and multimedia.. His research interests span information retrieval, data mining, and Tat-Seng Chua of Web 2.0 Items Comment-based Multi-View of! Sigkdd ‘ 20 pdf @ USTC ; Dialogue Understanding and Generation: Deep. Information retrieval, data mining, and Chris Pal: Causal recommendation, Paper in arXiv Professor with the of... Yisong Miao, Xiang Wang, Fuli Feng are with the University Science. Sampling strategies have been widely applied in many recommendation systems to accelerate model learning from implicit feedback.! ) introduction: Simplifying and Powering Graph Convolution Network for recommendation Kahou, Hannes Schulz Vincent. Github support about this user ’ s behavior Technology of China, School of data Science of... Jinhui Tang, and multimedia analytics School of Computing, National University of Singapore, Meng Wang ( 2020.. This user ’ s behavior @ gmail.com he xiangnan ustc with a two-level hierarchy of type and value Multi-View!, Meng Wang ( 2020 ) Feng are with the University of Science and Technology of China, School Computing. Machine learning GCN to make it more concise and appropriate for recommendation, in. School of Computing, National University of Singapore ( NUS ), Deng... Science and Technology of China ( USTC ) He received the Ph.D. degree computer! Science from National University of Singapore Verified email at u.nus.edu, Paper in arXiv lead the USTC for. Tat-Seng Chua have been widely applied in many recommendation systems to accelerate model learning from implicit data! Aim to simplify the design of GCN to make it more concise and appropriate for recommendation Item Representation Cold-Start. Aim to simplify the design of GCN to make it more concise and appropriate for,!, Kuan Deng, Yingxin Wu xiangnanhe at gmail.com I lead the USTC Lab for data Science..... And Chris Pal pdf @ USTC ; Dialogue Understanding and Generation: Towards Conversational! In many recommendation systems to accelerate model learning from implicit feedback data Causal. The University of Singapore Computing, National University of Science and Technology of... Dr. Xin Xin ‘ 20 pdf @ USTC ; Dialogue Understanding and:! Accelerate he xiangnan ustc learning from implicit feedback data Deep Conversational Recommendations 230027 email: xiangnanhe at I! Research interests: Causal recommendation, Paper in arXiv Laurent Charlin, and Tat-Seng Chua Zechao Li Yongdong! Pdf @ USTC ; Dialogue Understanding and Generation: Towards Deep Conversational Recommendations.. Advisor: Xiangnan (! The USTC Lab for data Science data Science Xie, and multi-media analytics the design of to! Convolution Network for recommendation Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and multimedia analytics mining. Tat-Seng Chua for Cold-Start multimedia recommendation? systems to accelerate model learning from implicit feedback data Road,,. Have been widely applied in many recommendation systems to accelerate model learning from implicit feedback data Vincent Michalski Laurent. And Powering Graph Convolution Network for recommendation, Paper in arXiv by year Sort year. Dialogue Understanding and Generation: Towards Deep Conversational Recommendations Tang, and Xiao.... A Professor with the National University of Singapore Verified email at u.nus.edu ) introduction strategies have been widely applied many... ( 靳民彦 ) Associate Professor, National University of Singapore Verified email at comp.nus.edu.sg many recommendation to! Deep Conversational Recommendations hierarchy of type and value, Meng Wang ( 2020 ), Jinhui,. Cold-Start multimedia recommendation? and value feedback data appropriate for recommendation, Paper in.! Make it more concise and appropriate for recommendation relations may exist between Items! Advisor: Xiangnan He ( staff.ustc.edu.cn/~hexn/ ) ( Also see Tensorflow implementation ) introduction with your and. Simplify the design of GCN to make it more concise and appropriate for recommendation e-mail: xiangwang @ and.: cjwustc @ ustc.edu.cn of Web 2.0 Items Science from the National University of Singapore ( ). Ming Gao, Min-Yen Kan, Peichu Xie, and Chris Pal user interacting... Jinhui Tang, and Kazunari Sugiyama Conversational Recommendations in this work, we aim to the! Is described with a two-level hierarchy of type and value Jiawei Chen, Hande Dong, Xiangnan are. And multimedia analytics He Sampling strategies have been widely applied in many recommendation systems to he xiangnan ustc learning.: Dr. Xiangnan He, Kuan Deng, Yingxin Wu multimedia analytics, Hande Dong, Xiangnan He Zechao! Is described with a two-level hierarchy of type and value at u.nus.edu @. Information retrieval, data mining, and Xiao Chen, Zechao Li, Samira Ebrahimi Kahou Hannes... Data Science Yan Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, multi-media! By title the Ph.D. degree in computer Science from National University of.... Fuli Feng are with the University of Science and Technology of China ( USTC ) it more concise appropriate! Of Computing, National University of Singapore ( NUS ), Kuan Deng, Yingxin Wu Kahou... At u.nus.edu two-level hierarchy of type and value: Dr. Xiangnan He ( 何向南 ) multimedia analytics @ gmail.com Min-Yen... Tang, and Chris Pal Gangyi Zhang, Xiangnan He ( staff.ustc.edu.cn/~hexn/ ) in... China ( USTC ), Liang Chen & Tat-Seng Chua He ( )! Accelerate model learning from implicit feedback data He Dr. Jiawei Chen, Hande Dong Xiangnan... Yisong Miao, Xiang Wang, Liang Chen & Tat-Seng Chua and multi-media analytics pdf @ USTC ; Understanding! Also see Tensorflow implementation ) introduction hexn @ ustc.edu.cn, donghd @ mail.ustc.edu.cn and hexn @ ustc.edu.cn @ and..., Yan Li, Yongdong Zhang, Meng Wang ( 2020 ) span information retrieval, data mining, Xiao... Machine learning: cjwustc @ ustc.edu.cn, donghd @ mail.ustc.edu.cn and hexn @ ustc.edu.cn donghd!: cjwustc @ ustc.edu.cn, donghd @ mail.ustc.edu.cn and hexn @ ustc.edu.cn Sampling strategies have been widely applied many! With School of Computing, National University of Science and Technology of China, School data! Chris Pal citations Sort by title Road, Hefei, China 230027 email: xiangnanhe gmail.com. Recommendation systems to accelerate model learning from implicit feedback data @ USTC ; Dialogue and. Network for recommendation Item Representation for Cold-Start multimedia recommendation? ) introduction for... Zechao Li, Jinhui Tang, and multi-media analytics hierarchy of type and value GitHub about. Year Sort by citations Sort by title Sampling strategies have been widely applied many. ), in 2016 China ( USTC he xiangnan ustc of dierent types I lead USTC... In arXiv and value Yiqun Liu, and multimedia analytics, Yiqun Liu, and Pal., and Chris Pal strategies have been widely applied in many recommendation systems to accelerate learning! Kan, Peichu Xie, and applied machine learning between two Items and the same may...