Photo

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. 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 under the supervision of Prof. Yuncai Liu.

I am interested in topics including deep graph learning, energy-based learning, drug design & discovery, optimization for machine learning and decentralized AI. I like various sports, e.g., swimming, hiking & skiing.

Contact:       Bian's email   Twitter@yataobian
Research:      Google Scholar     ORCID



Job Openings: I am looking for highly motivated interns on research topics about graph neural nets, energy-based learning, optimization for machine learning or other related ones. The position will be currently Shenzhen based. Feel free to send your C.V. to me.

News

Activities

Conference Paper Reviewing

  • NeurIPS 2021, ICCV 2021, CVPR 2021, AAAI 2021, NeurIPS 2020, AAAI 2020, NeurIPS 2019, ICML 2019, AISTATS 2019, STOC 2018, ITCS 2017, NIPS 2016

Journal Paper Reviewing

  • JMLR

Teaching

Courses@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.
  • On Self-Distilling Graph Neural Network
    IJCAI 2021. Chen, Bian, Xiao, Rong, Xu, J. Huang [pdf]
  • Graph Information Bottleneck for Subgraph Recognition
    ICLR 2021. Yu, Xu, Rong, Bian, J. Huang, Ran [pdf]
  • Self-Supervised Graph Transformer on Large-Scale Molecular Data
    NeurIPS 2020. Rong*, Bian*, Xu, Xie, Wei, W. Huang, J. Huang [pdf] [video] [bib]
        
  • From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models
    ICML 2020. Sahin, Bian, Buhmann, Krause [pdf] [bib]
          @inproceedings{sahin2020sets,
            title={From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models},
            author={Sahin, Aytunc and Bian, Yatao and Buhmann, Joachim M and Krause, Andreas},
            booktitle={Proceedings of the 37th International Conference on Machine Learning},
            year={2020},
            publisher={PMLR},
          }
        
  • Provable Non-Convex Optimization and Algorithm Validation via Submodularity
    Doctoral thesis, ETH Zurich. Bian [pdf] [bib]
        @phdthesis{bian2019provable,
          title={Provable Non-Convex Optimization and Algorithm Validation via Submodularity},
          author={Bian, Yatao An},
          year={2019},
          school={ETH Zurich}
        }
      
  • Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference
    ICML 2019. Bian, Buhmann, Krause [pdf] [code] [poster] [bib]
        @inproceedings{bian2019optimalmeanfield,
          title={Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference},
          author={Bian, Yatao A. and Buhmann, Joachim M. and Krause, Andreas},
          booktitle={Proceedings of the 36th International Conference on Machine Learning},
          pages={644--653},
          year={2019},
          volume={97},
          series={Proceedings of Machine Learning Research},
          address={Long Beach, California, USA},
          month={09--15 Jun},
          publisher={PMLR},
        }
      
  • CoLA: Decentralized Linear Learning
    NeurIPS 2018. He*, Bian*, Jaggi [arXiv] [code] [poster] [bib]
        @inproceedings{he2018cola,
        title={COLA: Communication-Efficient Decentralized Linear Learning},
        author={He, Lie and Bian, An and Jaggi, Martin},
        booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
        pages = {4537--4547},
        year={2018}
        }
        
  • A Distributed Second-Order Algorithm You Can Trust
    ICML 2018. Duenner, Lucchi, Gargiani, Bian, Hofmann, Jaggi [paper] [bib]
      @inproceedings{Celestine2018trust,
        title={A Distributed Second-Order Algorithm You Can Trust},
        author={D{\"u}nner, Celestine and Lucchi, Aurelien and Gargiani, Matilde and Bian, An and Hofmann, Thomas and Jaggi, Martin},
        booktitle={ICML},
        pages={1357--1365},
        year={2018}
      }
      
  • Continuous DR-submodular Maximization: Structure and Algorithms
    NIPS 2017. Bian, Levy, Krause, Buhmann [arXiv] [code] [poster] [video] [bib]
    @inproceedings{biannips2017nonmonotone,
      title={Continuous DR-submodular Maximization: Structure and Algorithms},
      author={Bian, An and Levy, Kfir Y. and Krause, Andreas and Buhmann, Joachim M.},
      booktitle={Advances in Neural Information Processing Systems (NIPS)},
      pages={486--496},
      year={2017}
    }
    
  • Guarantees for Greedy Maximization of Non-submodular Functions with Applications
    ICML 2017. Bian, Buhmann, Krause, Tschiatschek [arXiv] [code] [poster] [bib]
    @inproceedings{bianicml2017guarantees,
      title={Guarantees for Greedy Maximization of Non-submodular Functions with Applications},
      author={Bian, Andrew An and Buhmann, Joachim M. and Krause, Andreas and Tschiatschek, Sebastian},
      booktitle={International Conference on Machine Learning (ICML)},
      pages={498--507},
      year={2017}
    }
    
  • Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains
    AISTATS 2017. Bian, Mirzasoleiman, Buhmann, Krause [full version][introductory post] [poster] [bib]
    @inproceedings{bian2017guaranteed,
      title={Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains},
      author={Bian, Andrew An and Mirzasoleiman, Baharan and Buhmann, Joachim M. and Krause, Andreas},
      booktitle={International Conference on Artificial Intelligence and Statistics (AISTATS)},
      pages={111--120},
      year={2017}
    }
    
  • Model Selection for Gaussian Process Regression
    GCPR 2017. *Gorbach, *Bian, Fischer, Bauer, Buhmann [paper] [bib]
    @inproceedings{gorbach2017model,
      title={Model Selection for Gaussian Process Regression},
      author={Gorbach, Nico S and Bian, Andrew An and Fischer, Benjamin and Bauer, Stefan and Buhmann, Joachim M},
      booktitle={German Conference on Pattern Recognition},
      pages={306--318},
      year={2017}
    }
    
  • Information-Theoretic Analysis of MAXCUT Algorithms
    ITA 2016. Bian, Gronskiy, Buhmann [pdf] [bib]
    @inproceedings{bian2016information,
        title={Information-theoretic analysis of MaxCut algorithms},
        author={Bian, Yatao and Gronskiy, Alexey and Buhmann, Joachim M},
        booktitle={IEEE Information Theory and Applications Workshop (ITA)},
        pages={1--5},
        url={http://people.inf.ethz.ch/ybian/docs/pa.pdf},
        year={2016}
    }
    
  • Greedy MAXCUT Algorithms and their Information Content
    ITW 2015. Bian, Gronskiy, Buhmann [short version] [full version][slides][bib]
    @inproceedings{ITW15_BianGB,
      author    = {Yatao Bian and Alexey Gronskiy and Joachim M. Buhmann},
      title     = {Greedy MaxCut algorithms and their information content},
      booktitle = {IEEE Information Theory Workshop (ITW) 2015, Jerusalem, Israel},
      pages     = {1--5},
      year      = {2015}
    }
    
  • Parallel Coordinate Descent Newton for Efficient L1-Regularized Minimization
    Technical report 2013. Bian, Li, Liu, Yang [pdf][code][bib]
    @article{bian2013parallel,
      title={Parallel Coordinate Descent Newton Method for Efficient L1-Regularized Minimization},
      author={Bian, An and Li, Xiong and Liu, Yuncai and Yang, Ming-Hsuan},
      journal={arXiv preprint arXiv:1306.4080},
      year={2013}
    }
    
  • Bundle CDN: A Highly Parallelized Approach for Large-scale L1-regularized Logistic Regression
    ECML 2013. Bian, Li, Cao, Liu [pdf][bib]
    @inproceedings{ecmlBian13,
      author    = {Yatao Bian and Xiong Li and Mingqi Cao and Yuncai Liu},
      title     = {Bundle CDN: A Highly Parallelized Approach for Large-Scale L1-Regularized
        Logistic Regression},
      booktitle = {ECML/PKDD},
      year      = {2013},
      pages     = {81-95}
    }
    
  • Parallelized Annealed Particle Filter for Real-Time Marker-Less Motion Tracking Via Heterogeneous Computing
    ICPR 2012. Bian, Zhao, Song, Liu [pdf][ bib]
    @inproceedings{icprbian12,
      author    = {Yatao Bian and Xu Zhao and Jian Song and Yuncai Liu},
      title     = {Parallelized Annealed Particle Filter for real-time marker-less motion tracking via heterogeneous computing},
      booktitle = {ICPR},
      year      = {2012},
      pages     = {2444-2447}
    }
    
  • Digitize Your Body and Action in 3-D at Over 10 FPS: Real Time Dense Voxel Reconstruction and Marker-less Motion Tracking via GPU Acceleration
    Champion technical report of AMD China Accelerated Computing Contest, 2011 [demo].
    Song*, Bian*, Yan, Zhao, Liu [pdf][bib]
    @article{songbian2013digitize,
      title={Digitize Your Body and Action in 3-D at Over 10 FPS: Real Time Dense Voxel
        Reconstruction and Marker-less Motion Tracking via GPU Acceleration},
      author={Song, Jian and Bian, Yatao and Yan, Junchi and Zhao, Xu and Liu, Yuncai},
      journal={arXiv preprint arXiv:1311.6811},
      year={2013}
    }
    


Previous Research 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.

Metal Parts Detection and Rustiness Estimation Under Complex Background (NTT Corp. Cooperate)
Team leader. Algorithm design, implementation and optimization.
Solved the problem of multi-view metal parts detection by training multiple templates. Used a novel template representation based on locally dominant gradient orientations.

Links

(Non-)Convex Optimization

Machine Learning

MISC

People

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