My research lies in machine learning and its applications. In particular, I am interested in broad topics in optimal transport theory, point process models, and their applications to graph modeling and analysis.
News
-
01/21/2022: "Text2Poster: Laying out Stylized Texts on Retrieved Images" is accepted by ICASSP 2022.
-
12/04/2020: "Learning Graphons via Structured Gromov-Wasserstein Barycenters" is accepted by AAAI 2021.
-
07/30/2020: I gave a talk about "Gromov-Wasserstein Factorization Model" at the Workshop on Optimal Transport, Topological Data Analysis and Applications to Shape and Machine Learning (OT-TDA).
-
06/01/2020: "Learning Autoencoders with Relational Regularization" is accepted by ICML 2020.
Selected Recent Papers (Full List)
-
He, Mingguo, Zhewei Wei, Zengfeng Huang, and Hongteng Xu. "BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation." The Conference on Neural Information and Processing System (NeurIPS) (2021).
-
Xie, Yujia, Yixiu Mao, Simiao Zuo, Hongteng Xu, Xiaojing Ye, Tuo Zhao, and Hongyuan Zha. "A Hypergradient Approach to Robust Regression without Correspondence." In International Conference on Learning Representations (ICLR), 2021.
-
Xu, Hongteng, Dixin Luo, Lawrence Carin, and Hongyuan Zha. "Learning Graphons via Structured Gromov-Wasserstein Barycenters." In AAAI Conference on Artificial Intelligence (AAAI), 2021.
-
Xu, Hongteng, Dixin Luo, Ricardo Henao, Svati Shah, and Lawrence Carin. "Learning Autoencoders with Relational Regularization." In International Conference on Machine Learning (ICML), pp. 10576-10586. PMLR, 2020.
-
Xu, Hongteng. "Gromov-Wasserstein Factorization Models for Graph Clustering." In AAAI Conference on Artificial Intelligence (AAAI), vol. 34, no. 04, pp. 6478-6485. 2020.