Tao Wen

Hi! I am Tao Wen (文韬), a CS PhD student at Dartmouth College (Fall 2024 - ), where I work with Prof. Yujun Yan and Prof. Yaoqing Yang. Previously, I obtained my M.S. in Data Science at NYU and B.S. in Statistics at RUC.

My current research interest is building efficient and trustworthy machine learning models, from the perspectives of robustness, model diagnostics, and statistical machine learning, etc. I have also worked on Graph Neural Networks. I sincerely thank my co-authors and advisors for their help in research.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github

profile photo

Publications
clean-usnob Elastic Representation: Mitigating Spurious Correlations for Group Robustness
Tao Wen, Zihan Wang, Quan Zhang, Qi Lei
AISTATS 2025
arxiv/code

Distributional Robustness; Spurious Correlations
We introduced Elastic Representation to address spurious correlations and improve worst-group accuracy without a severe sacrifice of overall accuracy. The proposed regularization method is simple, effective, and general-purpose.

clean-usnob Bridging Domain Adaptation and Graph Neural Networks: A Tensor-Based Framework for Effective Label Propagation
Tao Wen, Elynn Chen, Yuzhou Chen, Qi Lei
CPAL 2025
arxiv/code

Graph Neural Networks; Domain Adaptation
We developed an approach for domain adaptive graph classification and bridged traditional domain adaptation methods and graphs. The proposed framework based on Label Propagation can be readily intergrated with existing GNNs for graph classification in domain adaptation settings.

clean-usnob Tensor-view Topological Graph Neural Network
Tao Wen, Elynn Chen, Yuzhou Chen
AISTATS 2024
arxiv/code

Graph Neural Networks
We developed the first approach bridging tensor methods with multi-modal graph structural features. It efficiently amalgamates diverse graph features with tensor low-rank structures and achieves state-of-the-art performance on graph classification tasks.

Service

Journals: TNNLS

Conferences: NeurIPS 2025

Teaching

  • CS 74/274: Machine Learning and Statistical Data Analysis, Dartmouth, Head TA, Winter 2024.
  • DS-GA 1018: Probabilistic Time Series Analysis, NYU, Head TA, Fall 2023.

Miscellaneous

  • I'm from Szechuan. Some say I should do a chef rather than a PhD.
  • I'm a big fan of football. My favorite team is New England Patriots (with Tom Brady).
  • I'm a big fan of video games. My favorite game is Red Dead Redemption 2.
  • I'm also a big fan of US national parks. I have been to Yosemite, Joshua Tree, Death Valley, and Everglades in 2024. My dream NP is Glacier.

Template