Hans Hao-Hsun Hsu

me.jpg

Hi, my name is Hans Hao-Hsun Hsu. I am currently a research intern at Georgia Tech where I work with Pan Li on domain adaptation in graph machine learning. I am also looking for PhD positions starting in Fall 2025.

My current research interests lie in (1) geometric deep learning and its application to scientific discovery/engineering (2) trustworthy AI on graphs (reliability, robustness and explainability). My long term goal is to integrate these two areas, developing machines that are both reliable and applicable in scientific scenarios (usually characterized by data scarcity).

Previously, I was a machine learning researcher at Celeris Therapeutics, an Austria- and UK-based startup, working on PROTACs-related drug discovery projects. I obtained my M.S. degree (with high distinction) from the Technical University of Munich advised by Daniel Cremers, where I worked on uncertainty estimation in geometric deep learning. I also hold a B.S. degree from National Taiwan University.

Feel free to reach out to me for any collaboration or research opportunities.

selected publications

  1. TSA.png
    Structural Alignment Improves Graph Test-Time Adaptation
    Hans Hao-Hsun Hsu, Shikun Liu, Han Zhao, and Pan Li
    In Preprint , 2025
    Paper
  2. GATS_new.png
    What Makes Graph Neural Networks Miscalibrated?
    Hans Hao-Hsun Hsu, Yuesong Shen, Christian Tomani, and Daniel Cremers
    In Neural Information Processing Systems (NeurIPS) , 2022
    Paper Code
  3. graph_ece.png
    A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs
    Hans Hao-Hsun Hsu, Yuesong Shen, and Daniel Cremers
    In NeurIPS GLFrontiers , 2022
    Paper Code
  4. vae_ad_framework.png
    Automated Antenna Testing Using Encoder-Decoder-based Anomaly Detection
    Hans Hao-Hsun Hsu, Jiawen Xu, Ravi Sama, and Matthias Kovatsch
    In International Conference on Machine Learning and Applications (ICMLA) , 2021
    Paper

other research projects

  1. protac.png
    GraphPROTACs: Out Of Distribution DC50 Prediction
    Celeris Therapeutics, 3.2023 - 1.2024

    Curated a PROTAC dataset and proposed GraphPROTACs, achieving state-of-the-art generalizability (AUROC increased from 55% to 75%) and enhanced model interpretability, with further improvements from training on synthetic data.

    Paper
  2. pong.gif
    Adversarial Attacks on Reinforcement Learning Agents Trained with Self-Play
    Technical University of Munich, 11.2020 - 3.2021

    Researched training RL agents in multi-agent environments and examined their robustness through observation-based and adversarial policy attacks.

    Paper Code
  3. IMG_6989.png
    Neural Network Interpretability
    Technical University of Munich, 4.2020 - 8.2020

    Researched deep learning interpretability methods and explored their ability to interpret neural network prediction uncertainty.

    Paper Code