个人简介
礼欣,博士,博士后。吉林大学学士、硕士,师从孙吉贵教授。香港浸会大学(Hong Kong Baptist University)博士、博士后,师从Prof. William K. Cheung 与 Prof. Jiming Liu。曾作为访问学者访问University of Waterloo, Canada (Host: Prof. Pascal Poupart),作为高级访问学者访问University of Technology Sydney, Australia (Host: Prof. Ivor W. Tsang). 目前主要从事数据挖掘、深度学习、强化学习、表示学习的相关理论研究和技术应用。近年来以第一作者及通讯作者身份在ICML、IJCAI、AAAI、ECML-PKDD、IEEE TCYB、TOIS、TKDE等人工智能、机器学习领域的知名国际会议和期刊发表若干篇学术论文。自2010-2019年担任The IEEE Intelligent Informatics Bulletin, Assistant Managing Editor。
在学生指导方面,鼓励并推荐学生交流访问,指导的研究生同学曾赴香港浸会大学、香港理工大学、美国斯坦福大学、澳大利亚悉尼科技大学访问。指导的硕士研究生发表多篇CCF A类会议论文,CCF A类/SCI一区期刊论文,并获得国家奖学金。毕业研究生去向包括微软、阿里、字节跳动、腾讯、京东、美团,滴滴等知名企业,或中国招商银行(总行),中国工商银行(总行),中科院电子所,中科院信工所,中国外交部等企事业单位。
所获奖励
2019年, 北京理工大学优秀硕士学位论文(洪辉婷同学,李盛楠同学), 指导教师
2018年, 北京理工大学优秀硕士学位论文(刘琳同学), 指导教师
2017年, 全国大学生信息安全竞赛三等奖,指导教师
2016年, 北京理工大学优秀硕士学位论文(陈佳良同学), 指导教师
2015年, 中国大学MOOC优秀教师
2014年, 博创杯全国大学生嵌入式物联网设计大赛,华北赛区一等奖,全国总决赛二等奖,指导教师
研究领域
机器学习、深度(强化)学习、表示学习理论及应用,包括:复杂网络数据挖掘、城市计算、医疗及公共卫生领域的应用,如:疾病诊断/预测;以及深度学习/深度强化学习技术在工业大数据、机器人领域的应用
近期论文
查看导师新发文章
(温馨提示:请注意重名现象,建议点开原文通过作者单位确认)
(Deep) Reinforcement Learning
Hongyu Zang, Xin Li, Jie Yu, Chen Liu, Riashat Islam, Remi Tachet des Combes, Romain Laroche. "Behavior Prior Representation learning for Offline Reinforcement Learning" ICLR 2023
Riashat Islam*, Hongyu Zang*, Manan Tomar, Aniket Didolkar, Md Mofijul Islam, Samin Yeasar Arnob, Tariq Iqbal, Xin Li, Anirudh Goyal, Nicolas Heess, Alex Lamb. "Representation Learning in Deep RL via Discrete Information Bottleneck" AISTATS 2023
Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford. "Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information" preprint
Riashat Islam, Hongyu Zang, Anirudh Goyal, Alex Lamb, Kenji Kawaguchi, Xin Li, Romain Laroche, Yoshua Bengio, Remi Tachet des Combes. "Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning" NeurIPS 2022. (CCF A)
Hongyu Zang, Xin Li, Mingzhong Wang. "SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning" AAAI 2022. (CCF A)
Li Zhang, Xin Li, etc. "Off-Policy Differentiable Logic Reinforcement Learning" ECML/PKDD (2) 2021: 617-632. (CCF B)
Li Zhang, Xin Li, etc. "Universal Value Iteration Networks: When Spatially-invariant is Not Universal" AAAI 2020: 6778-6785. (CCF A)
Xinwen Wang, Xin Li, etc. "On Improving the Learning of Long-Term historical Information for Tasks with Partial Observability" IEEE International Conference on Data Science in Cyberspace: Big Data and Business Analytics, 2020.
Pengfei Zhu, Xin Li, Pascal Poupart, "On Improving Deep Reinforcement Learning for POMDPs". CoRR abs/1704.07978(2017). (cited over 104 times)
Xin Li, William K. Cheung, Jiming Liu, "Improving POMDP’s Tractability Via Belief Compression and Clustering", IEEE Transaction on Systems, Man and Cybernetics – Part B 40(1):125-136 Feb, 2010. (CCF A)
Xin Li, William K. Cheung, Jiming Liu, Zhili Wu, "A Novel Orthogonal NMF-Based Belief Compression for POMDPs", in Proceedings of 24th International Conference on Machine Learning (ICML), Pages: 537 -544 Corvallis, OR, US, 2007. (CCF A)
Representation Learning and More
Qianyu Chen, Xin Li, Kunnan Geng, Mingzhong Wang. "Context-aware Safe Medication Recommendations with Molecular Graph and DDI Graph Embedding" AAAI 2023.
Fuhao Yang, Xin Li, Min Wang, Hongyu Zang, Wei Pang, Mingzhong Wang. "WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series" AAAI 2023.
Huiting Hong, Xin Li, Yuangang Pan, Ivor W. Tsang. "Domain-Adversarial Network Alignment" IEEE TKDE 2022.
Hongyu Zang, Dongcheng Han, Xin Li, Zhifeng Wan, Mingzhong Wang. "CHA: Categorical Hierarchy-based Attention for Next POI Recommendation" ACM TOIS 2022.
Huiting Hong, Xin Li, Mingzhong Wang. "GANE: A Generative Adversarial Network Embedding" IEEE TNNLS 2020.
Li Liu, Xin Li, William K. Cheung, Lejian Liao. "Structural Representation Learning for User Alignment Across Social Networks" IEEE TKDE 2020.
Xin Li, Dongcheng Han, Jing He, Lejian Liao, Mingzhong Wang. "Next and Next New POI Recommendation via Latent Behavior Pattern Inference". ACM TOIS 2019.
Rui Ye, Xin Li, et al. "A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment", IJCAI 2019. (CCF A)
Jing He, Xin Li, Lejian Liao, et al, "Inferring Continuous Latent Preference on Transition Intervals for Next Point-of-Interest Recommendation" ECML/PKDD 2018. (CCF B)
Shengnan Li, Xin Li, et al. "Non-translational Alignment for Multi-relational Networks" IJCAI 2018. (CCF A)
Lin Liu, Xin Li, William K. Cheung, Chengcheng Xu, "A Structural Representation Learning for Multi-relational Networks" IJCAI 2017. (CCF A)
Jing He, Xin Li, Lejian Liao, "Category-aware Next Point-of-Interest Recommendation via Listwise Bayesian Personalized Ranking" IJCAI 2017. (CCF A)
Jing He, Xin Li, Lejian Liao, Dandan Song, William K. Cheung. "Inferring A Personalized Next Point-of-Interest Recommendation Model with Latent Behavior Patterns" AAAI 2016. (CCF A)
Li Liu, William K. Cheung, Xin Li, Lejian Liao. "Aligning Users Across Social Networks Using Network Embedding" IJCAI 2016. (CCF A)
学术兼职
IEEE, CCF 会员
The IEEE Intelligent Informatics Bulletin, Assistant Managing Editor (2010-2019)
CIKM, WSDM, AAAI, IJCAI, ICML, NeurIPS (高级)程序委员
TKDE, TOC, TNNLS, TOIS, TNSM, 电子学报等期刊审稿人