个人信息

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（导师：William K. Cheung教授与Jiming Liu教授）、博士后，University of Waterloo 访问学者 (Host: Prof. Pascal Poupart)，University of Technology Sydney高级访问学者 (Host: Prof. Ivor W. Tsang). 目前主要从事强化学习、图学习的理论研究和技术应用。近年来以第一作者或通讯作者在ICML、NeurIPS、ICLR、KDD、IJCAI、AAAI、TPAMI、TCYB、、TKDE、TOIS等人工智能、机器学习领域的知名国际会议及期刊发表多篇学术论文。2010-2019年曾担任The IEEE Intelligent Informatics Bulletin助理执行编辑。

在研究生培养方面、重视学生的国际交流，积极推荐学生赴香港浸会大学、香港理工大学、斯坦福大学、悉尼科技大学、新加坡A*STAR等世界知名学府及学术研究机构进行交流访问。指导本科生、硕士研究生、博士研究生发表多篇CCF A类会议论文，CCF A类/SCI一区期刊论文，并荣获国家奖学金。毕业研究生去向包括：微软、阿里巴巴、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。

科研方向

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、机器人及特定领域的应用。

代表性学术成果

以下文章列表按发表时年倒序排列(*为通讯作者)

[1] Qianyu Chen, Xin Li*, Yujie Fang, Mingzhong Wang: Advancing Confidence Calibration and Quantification in Medication Recommendation. KDD 2025, Canada (Accepted)(CCF A)

[2] Ruixiang Sun, Hongyu Zang, Xin Li*, Riashat Islam: Learning Latent Dynamic Robust Representations for World Models. ICML 2024, Austria (CCF A)

[3] Yujie Fang, Xin Li*, et al. : Improving GNN Calibration with Discriminative Ability: Insights and Strategies. AAAI Conference on Artificial Intelligence (AAAI), February, 2024, Canada. (CCF A)

[4] Min Wang, Xin Li*, et al.: MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components, AAAI Conference on Artificial Intelligence (AAAI), February, 2024, Canada. (CCF A)

[5] Hongyu Zang, Xin Li*, et al. : Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning. Thirty-seventh Conference on Neural Information Processing Systems 2023 (NeurIPS 2023). (CCF A)

[6] Xin Li*, et al. : Differentiable Logic Policy for Interpretable Deep Reinforcement Learning: A Study From an Optimization Perspective. IEEE Trans. Pattern Anal. Mach. Intell. 45(10): 11654-11667 (2023) (CCF A)

[7] Hongyu Zang, Xin Li*, et al. : Behavior Prior Representation learning for Offline Reinforcement Learning. Eleventh International Conference on Learning Representations, ICLR 2023

[8] Fuhao Yang, Xin Li*, et al.: WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series. AAAI Conference on Artificial Intelligence (AAAI), Pages:10754-10761, February, 2023, virtual, United States.(CCF A)

[9] Qianyu Chen, Xin Li*, et al.: Context-aware safe medication recommendations with molecular graph and DDI graph embedding. AAAI Conference on Artificial Intelligence (AAAI), pages:7053-7060, February, 2023, virtual, United States. (CCF A)

[10] 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. Thirty-sixth Conference on Neural Information Processing Systems 2022 (NeurIPS 2022) (CCF A)

[11] Huiting Hong, Xin Li*, Yuangang Pan, Ivor W. Tsang: Domain-Adversarial Network Alignment. IEEE Trans. Knowl. Data Eng. 34(7): 3211-3224 (2022) (CCF A)

[12] Hongyu Zang, Xin Li*, Mingzhong Wang: SimSR: Simple Distance-Based State Representations for Deep Reinforcement Learning. AAAI Conference on Artificial Intelligence (AAAI), Pages:8997-9005, February, 2022, virtual, Canada. (CCF A)

[13] Li Zhang, Xin Li*, et al.:Off-Policy Differentiable Logic Reinforcement Learning. ECML/PKDD (2) 2021: 617-632, Sept.2021, Basque Country, Spain. (CCF B)

[14] Li Liu, Xin Li*, William K. Cheung, Lejian Liao: Structural Representation Learning for User Alignment Across Social Networks. IEEE Trans. Knowl. Data Eng. 32(9): 1824-1837 (2020) (CCF A)

[15] Li Zhang, Xin Li*, et al. : Universal Value Iteration Networks: When Spatially-Invariant Is Not Universal. AAAI Conference on Artificial Intelligence (AAAI), Pages: 6778-6785, February, 2020, New York City, USA. (CCF A)

[16] Huiting Hong, Xin Li*, Mingzhong Wang: GANE: A Generative Adversarial Network Embedding. IEEE Trans. Neural Networks Learn. Syst. 31(7): 2325-2335 (2020) (SCI一区)

[17] Xin Li, et al.: Next and Next New POI Recommendation via Latent Behavior Pattern Inference. ACM Trans. Inf. Syst. 37(4): 46:1-46:28 (2019) (CCF A)

[18] Rui Ye, Xin Li*, et al. : A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment. The 28^th International Joint Conference on Artificial Intelligence (IJCAI), Pages: 4135-4141, Aug., 2019, Macao, China. (CCF A)

[19] Shengnan Li, Xin Li*, et al. : Non-translational Alignment for Multi-relational Networks. The 27^th International Joint Conference on Artificial Intelligence (IJCAI), Pages: 4180-4186, Aug., 2018, Stockholm, Sweden. (CCF A)

[20] Xin Li*, et al.:A Time-Aware Personalized Point-of-Interest Recommendation via High-Order Tensor Factorization. ACM Trans. Inf. Syst. 35(4): 31:1-31:23 (2017) (CCF A)

[21] Lin Liu, Xin Li*, William K. Cheung, Chengcheng Xu : A Structural Representation Learning for Multi-relational Networks. The 26^th International Joint Conference on Artificial Intelligence (IJCAI), Pages: 4047-4053, Aug., 2017, Melbourne, Australia. Source Code：https://github.com/luoxiaolin521/MNE (CCF A)

[22] Jing He, Xin Li*, Lejian Liao : Category-aware Next Point-of-Interest Recommendation via Listwise Bayesian Personalized Ranking. The 26^th International Joint Conference on Artificial Intelligence (IJCAI), Pages: 1837-1843, Aug., 2017, Melbourne, Australia. Source Code：https://github.com/skyhejing/IJCAI2017 (CCF A)

[23] 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 Conference on Artificial Intelligence (AAAI), Pages: 137-143, February, 2016, Phoenix, Arizona USA. Source Code：https://github.com/skyhejing/AAAI2016 (CCF A)

[24] Li Liu, William K. Cheung, Xin Li*, Lejian Liao: Aligning Users Across Social Networks Using Network Embedding. The 25^th International Joint Conf0erence on Artificial Intelligence (IJCAI), Pages: 1774-1780, July, 2016, New York City, USA. Source Code：https://github.com/ColaLL/AcrossNetworkEmbeddingSynthetic (CCF A)

[25] 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 (2010) (SCI一区)

[26] Xin Li*, William K. Cheung, Jiming Liu, Zhili Wu : A Novel Orthogonal NMF-Based Belief Compression for POMDPs. The 24th International Conference on Machine Learning (ICML), Pages: 537 -544 Corvallis, OR, US, 2007. (CCF A)

arXiv高引论文

[1] Pengfei Zhu, Xin Li*, Pascal Poupart, “On Improving Deep Reinforcement Learning for POMDPs ”. CoRR abs/1704.07978(2017) . Source Code：https://github.com/bit1029public/ADRQN

承担科研情况

作为项目负责人、子课题负责人，获得基金支持的项目包括：

2018.01 - 2021.12 国家自然科学基金面上项目： 6177XXXX，项目负责人 

2018.09 - 2021.09 国家重点研发计划，网络空间安全重点专项，面向XX的智能问答匹配技术研究，子课题负责人

2017.09 - 2020.09 国家重点研发计划，网络空间安全重点专项，XX发现与XX预测项目，子课题负责人

2014.01 - 2016.12 国家自然科学基金青年项目：6130XXXX，项目负责人

2013.01 - 2017.08 国家重点基础研究发展计划(973项目)：社交网络分析与网络信息传播，子课题负责人 

2012.01 - 2014.12 教育部博士点新教师基金：2011110112XXXX，项目负责人 

2012.01 - 2013.12 威尼斯87978797基础研究基金，项目负责人

2010.01 - 2011.12 符号计算与知识工程教育部重点实验室对外开放基金项目，项目负责人

所获奖励

　　2019年， 威尼斯87978797优秀硕士学位论文(洪辉婷同学，李盛楠同学)， 指导教师

　　2018年， 威尼斯87978797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， 威尼斯87978797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

社会兼职

[1] IEEE, CCF 会员

[2] The IEEE Intelligent Informatics Bulletin, Assistant Managing Editor (2010-2019)

[3] ICML, ICLR, NeurIPS, IJCAI, AAAI (高级)程序委员

[4] TKDE, TOC, TNNLS, TOIS, TNSM, 电子学报等期刊审稿人

备注

课题组常年招收博士研究生1人、硕士生2-3人、以及高年级本科生。欢迎对我组研究方向感兴趣的同学通过Email、电话、或短信与我联系。特别对我组表示学习与深度强化学习工作感兴趣的同学欢迎访问：https://bit1029public.github.io/