Hi, this is Yatao (name). I am a senior research scientist at Tencent AI Lab. I received my Doctor of Sciences degree from the Institute for Machine Learning at ETH Zürich Computer Science. I was supervised by Prof. Joachim M. Buhmann and also worked closely with Prof. Andreas Krause (PhD co-examiner). Before that I obtained both of my M.Sc.Eng. and B.Sc.Eng. from Shanghai Jiao Tong University.

I am motivated by developing principled and reliable algorithms for graph representation learning, with the aim of solving real-world problems like molecular modelling. Some of my research topics include: graph foundation models, interpretable and OOD robust graph learning, trustworthy large models and neural sets. I like various sports, e.g., swimming, hiking & skiing.
Contact:       Bian's email   Twitter@yataobian
Research:      Google Scholar     ORCID


Academic Activities


Conference Reviewing/PC

Journal Reviewing


Industry Experience

  • Google Research
  • Tencent AI

Teaching Experience @ETH Zürich

  • TA to Prof. Thomas Hofmann
    "Computational intelligence lab" (Spring 2018)
  • TA to Prof. Joachim M. Buhmann
    "Machine Learning" (Fall 2017) [website]
  • TA to Prof. Thomas Hofmann
    "Computational intelligence lab" (Spring 2017) [website]
  • TA to Prof. Joachim M. Buhmann
    "Machine Learning" (Fall 2016)
  • TA to Prof. Thomas Hofmann
    "Computational intelligence lab" (Spring 2016) [website]
  • TA to Prof. Joachim M. Buhmann
    "Machine Learning" (Fall 2015)
  • TA to Prof. Joachim M. Buhmann
    "Introduction to Machine Learning" (Fall 2014)

Selected Papers & Code

◽Notice: My name was also written as A. A. Bian.
Copyright warning: The copyright of each published paper belongs to the respective publisher. The local copy is only for non-commercial, personal use.

Research Projects

Ongoing Projects:

◾ Trustworthy AI, AI Reliability
Develop principled methods for model interpretation, learning with fairness and reliable graph learning. Ensure reliable usage of large language models (LLMs), such as chatGPT-like models.

For a recent paper, please see Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning. Here is the project page

◾ (Graph) Out-of-distribution (OOD) learning in drug AI
The problem of distribution shift is prevalent in various tasks of AI-aided drug discovery. For example, for the task of structure-based virtual screening, the models are often trained on data of known protein targets but have to be tested on unknown targets. Meanwhile, the current model backbone of Drug AI is the graph neural networks (GNNs).

We have built an OOD Dataset Curator and Benchmark for AI-aided Drug Discovery, for details please refer to the project page.

The main research directions include, but not limited to the following:
- Design OOD learning algorithms and theory, such as algorithms for domain generalization and domain adaptation scenarios, so that Drug AI algorithms could work efficiently in the scenarios of distribution shift.
- The combination of OOD learning and deep graph learning. On one hand, one could improve the generalization ability of deep graph learning algorithms in the OOD scenarios (graph OOD learning); on the other hand, one could utilize the strong modeling capabilities to design better OOD algorithms.

◾ Neural set function learning
Parameterize generic set functions using neural backbones (such as DeepSet-style models and GNN-style models). Develop principled algorithms and theory for set function learning.

For a recent paper, please see Learning Neural Set Functions Under the Optimal Subset Oracle. Here is the project page

Previous Projects:

Fast Human Motion Tracking (National Champion in China Accelerated Computing Contest, 2011)
In charge of PAPF design, GPU implementation and optimization.
Proposed Parallelized Annealed Particle Filter (PAPF) algorithm via heterogeneous computing and built a real-time marker-less motion tracking system. Achieved 399 times speedup.

3D Monocular Human Upper Body Pose Estimation (Samsung Corp. Cooperate)
Team leader. Algorithm design, implementation and optimization.
Conducted human upper body pose estimation via generative algorithms . Incorporating generative models and discriminative algorithms to pursue better performance.


(Non-)Convex Optimization

Machine Learning



I collaborate(d) with the following people and feel extremely lucky about that.

I'm extremely thankful for working with these excellent interns and students:

  • Benjamin Fischer (Master student @ETH -> Now @Ergon Informatik AG, Switzerland)
  • Peiyuan Zhang (Master student @ETH)
  • Matilde Gargiani (Master student @ETH -> Now PhD @ETH)
  • Lie He (Master student @EPFL -> Now PhD @EPFL)
  • Hehuan Ma (PhD @University of Texas at Arlington)
  • Yuzhao Chen (Master student @Tsinghua University -> @Tencent)
  • Junchi Yu (PhD @Chinese Academy of Sciences)
  • Lixuan Lang (Bachelor @UC San Diego -> Master student @ETH)
  • Huaisheng Zhu (Bachelor @SUSTech -> PhD @PennState, USA)
  • Erxue Min (PhD @The University of Manchester)
  • Jiying Zhang (Master student @Tsinghua University)
  • Weizhi An (PhD @University of Texas at Arlington)
  • Heng Chang (PhD @Tsinghua University -> Now @Huawei)
  • Xinyuan Huang (Master student @ETH -> Now @Apple)
  • Guoji Fu (Master student @SUSTech -> Now PhD @National University of Singapore)
  • Yuanfeng Ji (PhD @The University of Hong Kong)
  • Lu Zhang (PhD @Fudan University -> Now @Tencent)
  • Zijing Ou (Bachelor @Sun Yat-sen University -> PhD @Imperial College London, UK)
  • Ziqiao Zhang (PhD @Fudan University)
  • Fei Li (PhD @Fudan University)
  • Yongqiang Chen (PhD @The Chinese University of Hong Kong)
  • Binghui Xie (PhD @The Chinese University of Hong Kong)
  • Liang Chen (PhD @The Chinese University of Hong Kong)
  • Yuchang Zhu (PhD @Sun Yat-sen University)