罗迪新 - 北京理工大学

个人简介

罗迪新，博士，预聘助理教授、特别副研究员，硕士生导师。于上海交通大学获得学士和博士学位，博士在读期间于美国佐治亚理工学院访学。曾任加拿大多伦多大学和美国杜克大学博士后、研究员。主要研究方向包括主要研究方向包括数据挖掘与机器学习，尤其是无监督和弱监督场景下的多模态学习，跨模态匹配与生成，及其在视频理解和3D内容生成中的应用。已发表领域顶级国际会议及期刊论文20余篇，其中以第一作者或通讯作者发表CCF-A类论文十余篇（如TPAMI、ACM-Multimedia、ICML、NeurIPS、AAAI、IJCAI、TKDE等），申请国家发明专利7项，已授权5项，主持国家自然科学基金1项。长期担任ICML、NeurIPS、AAAI、ACM Multimedia等多个国际顶级会议程序委员会委员，以及TKDE、TNNLS等顶级期刊审稿人。社会兼职 CCF会员 The Workshop on Data-driven Knowledge Mobilization, CASCON 2016，联合主席长期担任ICML、NeurIPS、AAAI、ACMMultimedia等多个国际顶级会议程序委员会委员长期担任TKDE、TNNLS等顶级期刊审稿人

研究领域

数据挖掘、机器学习

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）

AAAI Privacy-Preserved Evolutionary Graph Modeling via Gromov-Wasserstein Autoregression Xiang, Yue, Luo, Dixin, and Xu, Hongteng In Proceedings of the AAAI Conference on Artificial Intelligence 2023 PAMI Differentiable Hierarchical Optimal Transport for Robust Multi-View Learning Luo, Dixin, Xu, Hongteng, and Carin, Lawrence IEEE Transactions on Pattern Analysis and Machine Intelligence 2022 ACMMM Weakly-Supervised Temporal Action Alignment Driven by Unbalanced Spectral Fused Gromov-Wasserstein Distance Luo, Dixin, Wang, Yutong, Yue, Angxiao, and Xu, Hongteng In Proceedings of the 30th ACM International Conference on Multimedia 2022 PAMI Representing graphs via Gromov-Wasserstein factorization Xu, Hongteng, Liu, Jiachang, Luo, Dixin, and Carin, Lawrence IEEE Transactions on Pattern Analysis and Machine Intelligence 2022 arXiv Learning Graphon Autoencoders for Generative Graph Modeling Xu, Hongteng, Zhao, Peilin, Huang, Junzhou, and Luo, Dixin arXiv 2021 AAAI Learning graphons via structured gromov-wasserstein barycenters Xu, Hongteng, Luo, Dixin, Carin, Lawrence, and Zha, Hongyuan In AAAI 2021 ICML Learning autoencoders with relational regularization Xu, Hongteng, Luo, Dixin, Henao, Ricardo, Shah, Svati, and Carin, Lawrence In ICML 2020 arXiv Hierarchical optimal transport for robust multi-view learning Luo, Dixin, Xu, Hongteng, and Carin, Lawrence In arXiv 2020 arXiv Fused Gromov-Wasserstein Alignment for Hawkes Processes Luo, Dixin, Xu, Hongteng, and Carin, Lawrence In arXiv 2019 AISTATS Benefits from superposed hawkes processes Xu, Hongteng, Luo, Dixin, Chen, Xu, and Carin, Lawrence In AISTATS 2018 IJCAI Online Continuous-Time Tensor Factorization Based on Pairwise Interactive Point Processes. Xu, Hongteng, Luo, Dixin, and Carin, Lawrence In IJCAI 2018 ICML Learning Hawkes processes from short doubly-censored event sequences Xu, Hongteng, Luo, Dixin, and Zha, Hongyuan In ICML 2017 arXiv CASCONet: A Conference dataset Luo, Dixin, and Lyons, Kelly arXiv 2017 TKDE Learning mixtures of markov chains from aggregate data with structural constraints Luo, Dixin, Xu, Hongteng, Zhen, Yi, Dilkina, Bistra, Zha, Hongyuan, Yang, Xiaokang, and Zhang, Wenjun IEEE Transactions on Knowledge and Data Engineering 2016 IJCAI Multi-task multi-dimensional hawkes processes for modeling event sequences Luo, Dixin, Xu, Hongteng, Zhen, Yi, Ning, Xia, Zha, Hongyuan, Yang, Xiaokang, and Zhang, Wenjun In IJCAI 2015 AAAI Dictionary learning with mutually reinforcing group-graph structures Xu, Hongteng, Yu, Licheng, Luo, Dixin, Zha, Hongyuan, and Xu, Yi In AAAI 2015 TB You are what you watch and when you watch: Inferring household structures from IPTV viewing data Luo, Dixin, Xu, Hongteng, Zha, Hongyuan, Du, Jun, Xie, Rong, Yang, Xiaokang, and Zhang, Wenjun IEEE Transactions on Broadcasting 2014