Ph.D. Candidate @ Tsinghua CS

Visiting Student @ Stanford MS&E

Image 1 Image 2 Image 2 Image 2

liujiashuo77@gmail.com


About Me

Hi, Im Jiashuo! I'm a fourth-year Ph.D. candidate in the Department of Computer Science & Technology at Tsinghua University, advised by Prof. Peng Cui. I am currently a visiting student researcher at Prof. Jose H. Blanchet's group in the Department of Management Science & Engineering at Stanford University. I work remotely with Prof. Hongseok Namkoong in the Decision, Risk, and Operations division at Columbia Business School. I am also lucky to work with Prof. Bo Li.
My CV is here: (English/ Chinese).

My research lies at the interface of machine learning and operations research, including:

  • Generalization under Distribution Shifts: Theoretical foundations and tools for understanding real-world distribution shifts;
  • Data Heterogeneity: Algorithms to model and exploit data heterogeneity under distribution shifts;
  • Distributionally robust optimization: Addressing the over-pessimism problem in real applications.

Invited Tutorials

  1. [2]
    Model the Data Heterogeneity for Out-of-Distribution Generalization Speakers: Peng Cui, Jiashuo Liu, Bo Li

    Tutorial at SIAM International Conference on Data Mining 2024 (SDM24)

  2. [1]
    Modeling & Exploiting Data Heterogeneity under Distribution Shifts [slides] [video] Speakers: Jiashuo Liu, Tiffany (Tianhui) Cai, Peng Cui, Hongseok Namkoong Invited Panelists: Aditi Raghunathan, Sara Beery, Shalmali Joshi, Dominik Rothenhäusler

    Tutorial at Conference on Neural Information Processing Systems 2023 (NeurIPS 2023)

Selected Papers
The full list of publications can be found in the publications page.
* indicates equal contributions.

Topic 1: Generalization under Distribution Shifts

  1. [4]
    Jiashuo Liu, Jiayun Wu, Jie Peng, Xiaoyu Wu, Yang Zheng, Bo Li, Peng Cui Enhancing Distributional Stability among Sub-populations AISTATS 2024, the 27th International Conference on Artificial Intelligence and Statistics [paper] [GitHub]
  2. [3]
    Yingtian Zou, Kenji Kawaguchi, Yingnan Liu, Jiashuo Liu, Mong-Li Lee, Wynne Hsu Towards Robust Out-of-Distribution Generalization Bounds via Sharpness ICLR 2024, the 12th International Conference on Learning Representations.
    Spotlight presentation (Top 5%). [paper]
  3. [2]
    Jiashuo Liu*, Tianyu Wang*, Peng Cui, Hongseok Namkoong On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets NeurIPS 2023, Datasets and Benchmarks Track,
    the 37th Conference on Neural Information Processing Systems. [paper] [GitHub]
    • Python Package: WhyShift contains our tabular benchmark & tools for performance diagnosis, including risk region analysis and DISDE.
  4. [1]
    Jiashuo Liu*, Zheyan Shen*, Yue He, Xingxuan Zhang, Renzhe Xu, Han Yu, Peng Cui. Towards Out-of-Distribution Generalization: A Survey Under Review at IEEE TPAMI.
    [paper] [website] [pageviews>20k]

Topic 2: Data Heterogeneity

  1. [4]
    Jiashuo Liu, Jiayun Wu, Bo Li, Peng Cui. Predictive Heterogeneity: Measures and Applications Revise & Resubmit at JMLR.
    [paper]
  2. [3]
    Jiashuo Liu, Jiayun Wu, Renjie Pi, Renzhe Xu, Xingxuan Zhang, Bo Li and Peng Cui Measure the Predictive Heterogeneity ICLR 2023, the 11th International Conference on Learning Representations.
    [paper]
  3. [2]
    Jiashuo Liu*, Zheyuan Hu*, Peng Cui, Bo Li, Zheyan Shen Kernelized Heterogeneous Risk Minimization NeurIPS 2021, the 35th Conference on Neural Information Processing Systems
    [paper] [code]
  4. [1]
    Jiashuo Liu, Zheyuan Hu, Peng Cui, Bo Li, Zheyan Shen Heterogeneous Risk Minimization ICML 2021, the 38th International Conference on Machine Learning.
    Short talk (Top 21.5%). [paper] [code]

Topic 3: Distributionally Robust Optimization

  1. [4]
    Jiashuo Liu, Jiayun Wu, Tianyu Wang, Hao Zou, Peng Cui Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications NeurIPS DistShift 2023, in NeurIPS 2023 Workshop on Distribution Shifts.
    [workshop paper] [full paper]
  2. [3]
    Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang and Bo Li Distributionally Robust Learning with Stable Adversarial Training IEEE TKDE 2022, IEEE Transactions on Knowledge and Data Engineering.
    [paper]
  3. [2]
    Jiashuo Liu*, Jiayun Wu*, Bo Li and Peng Cui. Distributionally Robust Optimization with Data Geometry NeurIPS 2022, the 36th Conference on Neural Information Processing Systems.
    Spotlight presentation (Top 5.2%). [paper]
  4. [1]
    Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li and Yishi Lin Stable Adversarial Learning under Distributional Shifts AAAI 2021, the 35th AAAI Conference on Artificial Intelligence.
    [paper] [code]

2024

  1. [18]
    Han Yu, Xingxuan Zhang, Renzhe Xu, Jiashuo Liu, Yue He, Peng Cui Rethinking the Evaluation Protocol of Domain Generalization CVPR 2024, the Conference on Computer Vision and Pattern Recognition 2024
    [paper]
  2. [17]
    Fengda Zhang, Qianpei He, Kun Kuang, Jiashuo Liu, Long Chen, Chao Wu, Jun Xiao, Hanwang Zhang Distributionally Generative Augmentation for Fair Facial Attribute Classification CVPR 2024, the Conference on Computer Vision and Pattern Recognition 2024
  3. [16]
    Jiashuo Liu, Jiayun Wu, Jie Peng, Xiaoyu Wu, Yang Zheng, Bo Li, Peng Cui Enhancing Distributional Stability among Sub-populations AISTATS 2024, the 27th International Conference on Artificial Intelligence and Statistics
    [paper] [GitHub]
  4. [15]
    Yingtian Zou, Kenji Kawaguchi, Yingnan Liu, Jiashuo Liu, Mong-Li Lee, Wynne Hsu Towards Robust Out-of-Distribution Generalization Bounds via Sharpness ICLR 2024, the 12th International Conference on Learning Representations.
    Spotlight presentation (Top 5%). [paper]

2023

  1. [14]
    Jiashuo Liu, Jiayun Wu, Tianyu Wang, Hao Zou, Peng Cui Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications NeurIPS 2023 DistShift Workshop, in NeurIPS 2023 Workshop on Distribution Shifts.
    [workshop paper] [full paper]
  2. [13]
    Jiashuo Liu*, Tianyu Wang*, Peng Cui, Hongseok Namkoong On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets NeurIPS 2023, Datasets and Benchmarks Track
    the 37th Conference on Neural Information Processing Systems. [paper][code] [python package] [downloads>2.6k]
  3. [12]
    Jie Peng*, Hao Zou*, Jiashuo Liu, Shaoming Li, Yibao Jiang, Jian Pei and Peng Cui Offline Policy Evaluation in Large Action Spaces via Outcome-Oriented Action Grouping WWW 2023, the ACM Web Conference 2023. [paper]
  4. [11]
    Jiashuo Liu, Jiayun Wu, Renjie Pi, Renzhe Xu, Xingxuan Zhang, Bo Li and Peng Cui Measure the Predictive Heterogeneity ICLR 2023, the 11th International Conference on Learning Representations.
    [paper]

2022

  1. [10]
    Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang and Bo Li Distributionally Robust Learning with Stable Adversarial Training IEEE TKDE 2022, IEEE Transactions on Knowledge and Data Engineering.
    [paper]
  2. [9]
    Jiashuo Liu*, Jiayun Wu*, Bo Li and Peng Cui. Distributionally Robust Optimization with Data Geometry NeurIPS 2022, the 36th Conference on Neural Information Processing Systems.
    Spotlight presentation (Top 5.2%). [paper]
  3. [8]
    Dacheng Xu, Benda Xu, Erjin Bao, Yiyang Wu, Aiqiang Zhang, Yuyi Wang, Geliang Zhang, Yu Xu, Ziyi Guo, Jihui Pei, Hanyang Mao, Jiashuo Liu, Zhe Wang, Shaomin Chen. Towards the ultimate PMT waveform analysis for neutrino and dark matter experiments JINST 2022, the Journal of Instrumentation.
    [paper]
  4. [7]
    Zimu Wang, Yue He, Jiashuo Liu, Wenchao Zou, Philip Yu, Peng Cui Invariant Preference Learning for General Debiasing in Recommendation KDD 2022, the SIGKDD Conference on Knowledge Discovery and Data Mining.
    [paper]

2021

  1. [6]
    Chongxuan Li, Kun Xu, Jun Zhu, Jiashuo Liu, Bo Zhang Triple Generative Adversarial Networks TPAMI 2021, the Transactions on Pattern Analysis and Machine Intelligence.
    [paper]
  2. [5]
    Jiashuo Liu*, Zheyuan Hu*, Peng Cui, Bo Li, Zheyan Shen Kernelized Heterogeneous Risk Minimization NeurIPS 2021, the 35th Conference on Neural Information Processing Systems.
    [paper] [code]
  3. [4]
    Jiashuo Liu, Zheyuan Hu, Peng Cui, Bo Li, Zheyan Shen Heterogeneous Risk Minimization ICML 2021, the 38th International Conference on Machine Learning.
    Short talk (Top 21.5%). [paper] [code]
  4. [3]
    Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li and Yishi Lin Stable Adversarial Learning under Distributional Shifts AAAI 2021, the AAAI Conference on Artificial Intelligence.
    [paper] [code]
  5. [2]
    Haoxin Liu, Ziwei Zhang, Peng Cui, Yafeng Zhang, Qiang Cui, Jiashuo Liu, Wenwu Zhu Signed Graph Neural Network with Latent Groups KDD 2021, the SIGKDD Conference on Knowledge Discovery and Data Mining.
    [paper]

2020

  1. [1]
    Zheyan Shen, Peng Cui, Jiashuo Liu, Tong Zhang, Bo Li, Zhitang Chen Stable Learning via Differentiated Variable Decorrelation KDD 2020, the SIGKDD Conference on Knowledge Discovery and Data Mining.
    [paper]

Professional Services

Journal reviewer: Operations Research, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transactions on Multimedia (TMM)

Conference reviewer / Program committee: ICLR (2024), NeurIPS (2023), ICML (2022,2023,2024), UAI (2022,2023,2024), AAAI (2022), IJCAI (2022,2023), CVPR (2022,2023, 2024), ECCV (2024), ICCV (2023), CoLLAs (2022,2023,2024), AISTATS (2021,2023,2024)

Workshop reviewer / Program committee: NeurIPS DistShift (2023)


Awards and Fellowships
  • Tsinghua-Huawei Scholarship (2023)
  • Excellent Comprehensive Scholarship of Tsinghua University (for PhD. Student, 2022)
  • National Scholarship for Ph.D. (2021)
  • Apple Scholars in AI/ML Nomination (2021)
  • Excellent Undergraduate, Tsinghua University (2020, 10%)
  • TP-Link Scholarship (2019)
  • Toyota Scholarship (2018)
  • Excellent Academic Scholarship of Tsinghua University (2018, 2019)
  • Excellent Comprehensive Scholarship of Tsinghua University (2017, 5%)
  • Second-Class Freshmen Scholarship of Tsinghua University (2016~2019)

Teaching
  • Software Engineering (Fall 2019, 2020, 2021, 2022, Spring 2022, 2023 TA)
  • Object-oriented Programming (Summer 2022, TA)

Acknowledgements: based on the al-folio template by Maruan Al-Shedivat and Jiaming Song

PageViews (since July 16th, 2023): test page