Juho Lee

• Personal Webpage
• GitHub

Bayesian nonparametric models, random graphs

I’m a postdoc working with François Caron on Bayesian nonparametric models and random graphs. Before joining Oxford, I completed my PhD in computer science & engineering at POSTECH, South Korea. My thesis was about developing efficient posterior inference algorithms for Bayesian nonparametric models. I’m also interested in Bayesian deep learning and deep learning aided Bayesian modelling, especially with Bayesian nonparametric models.

Publications

2022

• G. K. Nicholls , J. E. Lee , C. H. Wu , C. U. Carmona , Valid belief updates for prequentially additive loss functions arising in Semi-Modular Inference, Jan. 2022.
  
  @article{Nicholls2022,
    author = {Nicholls, G. K. and Lee, J. E. and Wu, C. H. and Carmona, C. U.},
    month = jan,
    title = {Valid belief updates for prequentially additive loss functions arising in Semi-Modular Inference},
    year = {2022}
  }
  

2021

• J. E. Lee , G. K. Nicholls , Tree based credible set estimation, Statistics and Computing, vol. 31, 69, 2021.
  

  @article{lee21,
    title = {Tree based credible set estimation},
    author = {Lee, J. E. and Nicholls, G. K.},
    journal = {Statistics and Computing},
    pages = {69},
    volume = {31},
    note = {arXiv preprint arXiv:2012.13837},
    year = {2021}
  }
  

2020

• H. Xing , G. K. Nicholls , J. E. Lee , Distortion estimates for approximate Bayesian inference, in Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), 2020, vol. 124, 1208–1217.
  

  @inproceedings{Xing20UAI,
    author = {Xing, H. and Nicholls, G. K. and Lee, J. E.},
    title = {Distortion estimates for approximate {B}ayesian inference},
    booktitle = {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)},
    pages = {1208-1217},
    year = {2020},
    volume = {124},
    publisher = {PMLR}
  }
  

2019

• J. Lee , Y. Lee , J. Kim , A. Kosiorek , S. Choi , Y. W. Teh , Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks, in International Conference on Machine Learning (ICML), 2019.
  
  Project: bigbayes

  Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set, models used to address them should be permutation invariant. We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. The model consists of an encoder and a decoder, both of which rely on attention mechanisms. In an effort to reduce computational complexity, we introduce an attention scheme inspired by inducing point methods from sparse Gaussian process literature. It reduces the computation time of self-attention from quadratic to linear in the number of elements in the set. We show that our model is theoretically attractive and we evaluate it on a range of tasks, demonstrating the state-of-the-art performance compared to recent methods for set-structured data.

  @inproceedings{pmlr-v97-lee19d,
    title = {Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks},
    author = {Lee, Juho and Lee, Yoonho and Kim, Jungtaek and Kosiorek, Adam and Choi, Seungjin and Teh, Yee Whye},
    booktitle = {International Conference on Machine Learning (ICML)},
    year = {2019},
    series = {Proceedings of Machine Learning Research},
    month = jun,
    publisher = {PMLR}
  }
  

• J. Lee , L. James , S. Choi , F. Caron , A Bayesian model for sparse graphs with flexible degree distributionand overlapping community structure, in Artificial Intelligence and Statistics (AISTATS), 2019.
  
  Project: bigbayes

  @inproceedings{Lee2019,
    author = {Lee, Juho and James, Lancelot and Choi, Seungjin and Caron, Fran\c cois},
    title = {A Bayesian model for sparse graphs with flexible degree distributionand overlapping community structure},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    note = {ArXiv e-prints: 1810.01778},
    year = {2019},
    month = apr
  }
  

• F. Ayed , J. Lee , F. Caron , Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with Double Power-law Behavior, 2019.
  
  @unpublished{Ayed:Lee:Caron,
    author = {Ayed, F. and Lee, J. and Caron, F.},
    title = {Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with Double Power-law Behavior},
    year = {2019}
  }
  

• J. E. Lee , G. K. Nicholls , R. Ryder , Calibration procedures for approximate Bayesian credible sets, Bayesian Analysis, vol. 14, 1245–1269, 2019.
  

  @article{lee2018calibration,
    title = {Calibration procedures for approximate Bayesian credible sets},
    author = {Lee, J. E. and Nicholls, G. K. and Ryder, R.J.},
    journal = {Bayesian Analysis},
    volume = {14},
    pages = {1245-1269},
    year = {2019},
    publisher = {International Society for Bayesian Analysis}
  }
  

• H. Xing , G. K. Nicholls , J. E. Lee , Calibrated Approximate Bayesian Inference, in Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, 2019, 6912–6920.
  

  @inproceedings{XingNL19,
    author = {Xing, H. and Nicholls, G. K. and Lee, J. E.},
    title = {Calibrated Approximate Bayesian Inference},
    booktitle = {Proceedings of the 36th International Conference on Machine Learning,
                   {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
    pages = {6912--6920},
    year = {2019}
  }
  

2018

• J. Heo , H. Lee , S. Kim , J. Lee , K. Kim , E. Yang , S. Hwang , Uncertainty-aware attention for reliable interpretation and prediction, in Advances in Neural Information Processing Systems (NeurIPS), 2018.
  
  Project: bigbayes

  @inproceedings{Heo2018,
    title = {Uncertainty-aware attention for reliable interpretation and prediction},
    author = {Heo, J. and Lee, H. and Kim, S. and Lee, J. and Kim, K. and Yang, E. and Hwang, S.},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year = {2018}
  }
  

• H. Lee , J. Lee , S. Kim , E. Yang , S. Hwang , DropMax: adaptive variational softmax, in Advances in Neural Information Processing Systems (NeurIPS), 2018.
  
  Project: bigbayes

  @inproceedings{Lee2018,
    title = {DropMax: adaptive variational softmax},
    author = {Lee, H. and Lee, J. and Kim, S. and Yang, E. and Hwang, S.},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year = {2018}
  }
  

2017

• J. Lee , C. Heakulani , Z. Ghahramani , L. F. James , S. Choi , Bayesian inference on random simple graphs with power law degree distributions, in International Conference on Machine Learning (ICML), 2017.
  

  @inproceedings{Lee2017,
    title = {Bayesian inference on random simple graphs with power law degree distributions},
    author = {Lee, J. and Heakulani, C. and Ghahramani, Z. and James, L. F. and Choi, S.},
    booktitle = {International Conference on Machine Learning (ICML)},
    year = {2017}
  }
  

2016

• J. Lee , L. F. James , S. Choi , Finite-dimensional BFRY priors and variational Bayesian inference for power law models, in Advances in Neural Information Processing Systems (NeurIPS), 2016.
  

  @inproceedings{Lee2016,
    title = {Finite-dimensional {BFRY} priors and variational {B}ayesian inference for power law models},
    author = {Lee, J. and James, L. F. and Choi, S.},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year = {2016}
  }
  

2015

• J. Lee , S. Choi , Tree-guided MCMC inference for normalized random measure mixture models, in Advances in Neural Information Processing Systems (NeurIPS), 2015.
  

  @inproceedings{Lee2015a,
    title = {Tree-guided {MCMC} inference for normalized random measure mixture models},
    author = {Lee, J. and Choi, S.},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year = {2015}
  }
  

• J. Lee , S. Choi , Bayesian hierarchical clustering with exponential family: small-variance asymptotics and reducibility, in Artificial Intelligence and Statistics (AISTATS), 2015.
  

  @inproceedings{Lee2015b,
    title = {Bayesian hierarchical clustering with exponential family: small-variance asymptotics and reducibility},
    author = {Lee, J. and Choi, S.},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    year = {2015}
  }
  

2014

• J. Lee , S. Choi , Incremental tree-based inference with dependent normalized random measures, in Artificial Intelligence and Statistics (AISTATS), 2014.
  

  @inproceedings{Lee2014,
    title = {Incremental tree-based inference with dependent normalized random measures},
    author = {Lee, J. and Choi, S.},
    booktitle = {Artificial Intelligence and Statistics (AISTATS)},
    year = {2014}
  }