HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Fri, 17 Oct 2025 07:38:44 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"68f1f284-3d96" expires: Mon, 29 Dec 2025 08:15:51 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 1051:2680BD:878A98:98547D:6952365F accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 08:05:51 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210065-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766995552.679424,VS0,VE210 vary: Accept-Encoding x-fastly-request-id: b7847ee977472a3f4b80f95a9eec90ca7e594b4a content-length: 4988

Yatong Chen (陈雅桐)   Ph.D. Max Planck Institute for Intelligent Systems

About Me

I am a Research Group Leader in the Social Foundations of Computation Department at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, hosted by Professor Moritz Hardt.

I completed my Ph.D. from the Computer Science and Engineering Department at the University of California, Santa Cruz, where I was fortunate to be advised by Professor Yang Liu. My research focuses on the social aspect of machine learning, taking into account human decision subjects' responses when developing algorithmic systems. I was a student researcher at Google Brain hosted by Ehsan Amid and Rohan Anil in the summer of 2022. I was supported by the Chancellor’s Dissertation-Year Fellowship.

I received a MS in Statistics at Stanford University in 2019, where I worked with Professor Johan Ugander on node classification problem using semi-supervised learning. Before that, I received my BS in Energy and Resources Engineering and BA in Economics from Peking University in 2016.

Here's my CV (last updated January 2025) and contact info.



News:

[October 2025] We are organizing a workshop on Benchmarking and AI Evaluation at EurIPS 2025, submit your work!
[September 2025] One Spotlight paper accepted to NeurIPS 2025!

Publications

(* equal contribution)

Strategic Hypothesis Testing
Yatong Chen*, Safwan Hossian*, and Yiling Chen.
NeurIPS 2025. Spotlight, top 3%.
[arXiv]

To Give or Not to Give? The Impacts of Strategically Withheld Recourse
Yatong Chen, Andrew Estornell, Yevgeniy Vorobeychik and Yang Liu.
AISTATS 2025. (Preliminary version at NeurIPS 2023 Workshop on Algorithmic Fairness through the Lens of Time).

Performative Prediction with Bandit Feedback: Learning through Reparameterization
Yatong Chen, Wei Tang, Chien-Ju Ho and Yang Liu.
ICML 2024.
[ArXiv]

Learning to Incentivize Improvements from Strategic Agents
Yatong Chen, Jialu Wang and Yang Liu.
TMLR. (Preliminary version at ICML 2021 Workshop on Algorithmic Recourse, Best Paper Award).
[paper] [code]

Model Transferability with Responsive Decision Subjects
Yatong Chen, Zeyu Tang, Kun Zhang and Yang Liu.
ICML 2023. (Preliminary version at ICML 2022 Workshop on Adversarial Machine Learning Frontiers, Best Paper Award).
[paper] [talk slides] [code]

Incentivizing Recourse through Auditing in Strategic Classification
Andrew Estornell, Yatong Chen, Sammy Das, Yang Liu, Yevgeniy Vorobeychik .
IJCAI 2023.
[paper]

Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors
Zeyu Tang, Yatong Chen, Yang Liu and Kun Zhang.
ICLR 2023. (Preliminary version at NeurIPS 2022 Workshop on Algorthmic Fairness Through the Lens of Causality and Privacy).
[paper]

Fair Transferability Subject to Distribution Shift
Yatong Chen*, Reilly Raab*, Jialu Wang and Yang Liu.
Neurips 2022. (Preliminary version at NeurIPS 2021 Workshop on Algorithmic Fairness through the Lens of Causality and Robustness).
[arXiv]

Metric-Fair Classifier Derandomization
Jimmy Wu, Yatong Chen and Yang Liu.
ICML 2022. Spotlight Presentation.
[paper] [talk slides]

Decoupled Smoothing on Graphs
Alex Chin, Yatong Chen, Kristen M. Altenburger and Johan Ugander.
WWW 2019. Oral Presentation, top 5%.
[paper] [code] [talk slides]

Workshop Papers

Fast Implicit Constrained Optimization of Non-decomposable Objectives for Deep Networks
Yatong Chen, Abhishek Kumar, Yang Liu, Ehsan Amid.
Has it Trained Yet? NeurIPS 2022 Workshop.
[paper]

Fishy: Layerwise Fisher Approximation for Higher-order Neural Network Optimization
Abel Peirson*, Ehsan Amid*, Yatong Chen, Vladimir Feinberg, Manfred K Warmuth, Rohan Anil.
Has it Trained Yet? NeurIPS 2022 Workshop.
[paper]

Decoupled Smoothing In Probabilistic Soft Logic
Yatong Chen*, Bryan Tor*, Eriq Augustine and Lise Getoor.
15th International Workshop on Mining and Learning with Graphs.
[paper] [talk slides]

Distinctions

Chancellor’s Dissertation-Year Fellowship (only one recipient in the School of Engineering), 2023, UC Santa Cruz

Best Paper Award, ICML Workshop on New Frontiers in Adversarial Machine Learning (AdvML), 2022

Finalist, Google PhD Fellowship Program, 2022

Best Paper Award, ICML Workshop on Algorithmic Recourse, 2021

Baskin Engineering Fellowship for Anti-Racism Research (FARR), 2021, UC Santa Cruz

Regents Fellowship, 2019, UC Santa Cruz

Workshops/Conferences/Talks

UPenn Theory Seminar. Talk on Metric-Fair Classifier Derandomization. April 12, 2024.

International Conference on Machine Learning (ICML) 2022 in Baltimore. Talk on Metric-Fair Classifier Derandomization. July 19, 2022. [link]

Workshop on New Frontiers in Adversarial Machine Learning (AdvML Frontiers) 2022 in Baltimore. Talk on Model Transferability Subject to Distribution Shift. July 22, 2022. [link]

Workshop on Algorithmic Recourse (AR) 2021 virtual. Spotlight talk on Learning Linear Classifiers that Encourage Constructive Adaptation. July 24, 2021. [link]

Workshop on Consequential Decision Making in Dynamic Environments (CDMDE) 2020 virtual. Talk on Strategic Recourse in Linear Classifier . December 12, 2020. [link]

Mining and Learning Graph Workshop (MLG) 2020 virtual. Talk on Decoupled smoothing in Probabilisitc Soft Logic. August 24, 2020. [link]

The Web Conference (WWW) 2019 in San Francisco, USA. Talk on Decoupled smoothing on Graphs. May 17, 2019. [link]

Contact Information

Email: yatong.chen [at] tuebingen.mpg.de, ychen592 [at] ucsc.edu
[Google Scholar] [LinkedIn] [Twitter]