Publications

You may also find my recent articles on Google Scholar.

Preprints

• Over-parameterised shallow neural networks with asymmetrical node scaling: global convergence guarantees and feature learning
  François Caron, Fadhel Ayed, Paul Jung, Hoil Lee, Juho Lee, Hongseok Yang

• Hybrid generative-contrastive representation learning
  Saehoon Kim, Sungwoong Kim, Juho Lee

• Learning to pool in graph neural networks for extrapolation
  Jihoon Ko, Taehyung Kwon, Kijung Shin, Juho Lee

• Deep amortized clustering
  Juho Lee, Yoonho Lee, Yee Whye Teh
  A preliminary version of this work has been accepted to NeurIPS 2019 Sets & Partitions workshop as an oral presentation.

• Adaptive network sparsification with dependent variational beta-Bernoulli dropout
  Juho Lee, Saehoon Kim, Jaehong Yoon, Hae Beom Lee, Eunho Yang, Sung Ju Hwang

Journals

• Deep neural networks with dependent weights: Gaussian process mixture limit, heavy tails, sparsity and compressibility)
  Hoil Lee, Fadhel Ayed, Paul Jung, Juho Lee, Hongseok Yang, François Caron
  Journal of Machine Learning Research, September 2023

• A unified construction for series representations and finite approximations of completely random measures
  Juho Lee, Xenia Miscouridou, François Caron
  Bernoulli, August 2023

• The Normal-Generalised Gamma-Pareto process: A novel pure-jump Lévy process with flexible tail and jump-activity properties
  Fadhel Ayed, Juho Lee, François Caron
  Bayesian Anaylsis, December 2022

• Benefits of stochastic weight averaging in developing neural network radiation scheme for numerical weather prediction
  Hwan-Jin Song, Soonyoung Roh, Juho Lee, Giung Nam, Eunggu Yun, Jongmin Yoon, Park Sa Kim
  Journal of Advances in Modeling Earth Systems, October 2022

Conferences

• Model fusion through Bayesian optimization in language model fine-tuning
  Chaeyun Jang*, Hyungi Lee*, Jungtaek Kim^, and Juho Lee^
  (*: equal contribution, ^: equal advising)
  To appear in NeurIPS 2024 (spotlight presentation)

• Ex Uno Pluria: insights on ensembling in low precision number systems
  Giung Nam, Juho Lee
  To appear in NeurIPS 2024

• Learning infinitesimal generators of continuous symmetries from data
  Gyeonghoon Ko, Hyunsu Kim, Juho Lee
  To appear in NeurIPS 2024

• Stochastic optimal control for diffusion bridges in function spaces
  Byoungwoo Park, Jungwon Choi, Sungbin Lim^, Juho Lee^
  (^: equal advising)
  To appear in NeurIPS 2024

• Safeguard text-to-image diffusion models with human feedback inversion
  Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee
  To appear in ECCV 2024

• Variational partial group convolutions for input-aware partial equivariance of rotations and color-shifts
  Hyunsu Kim, Yegon Kim, Hongseok Yang, and Juho Lee
  ICML 2024

• A simple early exiting framework for accelerated sampling in diffusion models
  Taehong Moon, Moonseok Choi, EungGu Yun, Jongmin Yoon, Gayoung Lee, Jaewoong Cho, and Juho Lee
  ICML 2024

• Learning to explore for stochastic gradient MCMC
  Seunghyun Kim, Seohyeon Jung, Seonghyeon Kim, and Juho Lee
  ICML 2024

• Fast ensembling with diffusion Schrödinger bridge
  Hyunsu Kim, Jongmin Yoon, and Juho Lee
  ICLR 2024

• Sparse weight averaging with multiple particles for iterative magnitude pruning
  Moonseok Choi, Hyungi Lee, Giung Nam, and Juho Lee
  ICLR 2024

• Lipsum-FT: Robust fine-tuning of zero-shot models using random text guidance
  Giung Nam, Byeongho Heo, and Juho Lee
  ICLR 2024

• Enhancing transfer learning with flexible nonparametric posterior sampling
  Hyungi Lee, Giung Nam, Edwin Fong, and Juho Lee
  ICLR 2024

• Self-supervised dataset distillation for transfer learning
  Dong Bok Lee, Seanie Lee, Joonho Ko, Kenji Kawaguchi, Juho Lee, and Sung Ju Hwang
  ICLR 2024

• Spear and shield: adversarial attacks and defense methods for model-based link prediction on continuous-time dynamic graphs
  Dongjin Lee, Juho Lee, and Kijung Shin
  AAAI 2024

• Function Space Bayesian pseudocoreset for Bayesian neural networks
  Balhae Kim, Hyungi Lee, Juho Lee
  NeurIPS 2023

• Probabilistic imputation for time-series classification with missing data
  SeungHyun Kim*, Hyunsu Kim*, Eunggu Yun*, Hwangrae Lee, Jaehun Lee, Juho Lee
  (*: equal contribution)
  ICML 2023

• Traversing between modes in function space for fast ensembling
  Eunggu Yun*, Hyungi Lee*, Giung Nam*, Juho Lee
  (*: equal contribution)
  ICML 2023

• Regularizing towards soft equivariance under mixed symmetries
  Hyunsu Kim, Hyungi Lee, Hongseok Yang, Juho Lee
  ICML 2023

• Scalable set encoding with universal mini-batch consistency and unbiased full set gradient approximation
  Jeffrey Ryan Willette*, Seanie Lee*, Bruno Andreis, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang
  (*: equal contribution)
  ICML 2023

• Martingale posterior neural processes
  Hyungi Lee, Eunggu Yun, Giung Nam, Edwin Fong, Juho Lee
  ICLR 2023 (Notable top 25%)

• Decoupled training for long-tailed classification with stochastic representations
  Giung Nam*, Sunguk Jang*, Juho Lee
  (*: equal contribution)
  ICLR 2023

• A simple yet powerful deep active learning with snapshot ensembles
  Seohyeon Jung*, Sanghyun Kim*, Juho Lee
  (*: equal contribution)
  ICLR 2023

• Self-distillation for further pre-training of transformers
  Seanie Lee, Minki Kang, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi
  ICLR 2023

• Exploring the role of mean teachers in self-supervised masked auto-encoders
  Youngwan Lee*, Jeffrey Ryan Willette*, Jonghee Kim, Juho Lee, Sung Ju Hwang
  (*: equal contribution)
  ICLR 2023

• On divergence measures for Bayesian pseudocoresets
  Balhae Kim, Jungwon Choi, Seanie Lee, Yoonho Lee, Jung-Woo Ha, Juho Lee
  NeurIPS 2022

• Set-based meta-interpolation for few-task meta-learning
  Seanie Lee, Bruno Andreis, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang
  NeurIPS 2022

• Improving ensemble distillation with weight averaging and diversifying perturbation
  Giung Nam, Hyungi Lee, Byeongho Heo, Juho Lee
  ICML 2022
  Code

• Set based stochastic subsampling
  Bruno Andreis, Seanie Lee, A. Tuan Nguyen, Juho Lee, Eunho Yang, Sung Ju Hwang
  ICML 2022

• Scale mixtures of neural network Gaussian processes
  Hyungi Lee, Eunggu Yoon, Hongseok Yang, Juho Lee
  ICLR 2022

• Sequential Reptile: inter-task gradient alignment for multilingual learning
  Seanie Lee, Hae Beom Lee, Juho Lee, Sung Ju Hwang
  ICLR 2022

• Meta learning low rank covariance factors for energy-based deterministic uncertainty
  Jeffrey Ryan Willette, Hae Beom Lee, Juho Lee, Sung Ju Hwang
  ICLR 2022

• Diversity matters when learning from ensembles
  Giung Nam*, Jongmin Yoon*, Yoonho Lee, Juho Lee
  (*: equal contribution)
  NeurIPS 2021
  Code

• Mini-batch consistent slot set encoder for scalable set encoding
  Bruno Andreis, Jeffrey Ryan Willette, Juho Lee, Sung Ju Hwang
  NeurIPS 2021

• A multi-mode modulator for multi-domain few-shot classification
  Yanbin Liu, Juho Lee, Linchao Zhu, Ling Chen, Humphrey Shi, Yi Yang
  ICCV 2021

• Adversarial purification with score-based generative models
  Jongmin Yoon, Sung Ju Hwang, Juho Lee
  ICML 2021
  Code

• Learning to perturb word embeddings for out-of-distribution QA
  Seanie Lee, Minki Kang, Juho Lee, Sung Ju Hwang
  ACL 2021

• SetVAE: learning hierarchical composition for generative modeling of set-structured data
  Jinwoo Kim, Jaehoon Yoo, Juho Lee, Seunghoon Hong
  CVPR 2021
  Code

• Bootstrapping neural processes
  Juho Lee*, Yoonho Lee*, Jungtaek Kim, Eunho Yang, Sung Ju Hwang, Yee Whye Teh
  (*: equal contribution)
  Code
  NeurIPS 2020

• Neural complexity measures
  Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi
  Code
  NeurIPS 2020

• Cost-effective interactive attention learning with neural attention processes
  Jay Heo, Junhyeon Park, Hyewon Jeong, Kwang Joon Kim, Juho Lee, Eunho Yang, Sung Ju Hwang
  ICML 2020

• Deep mixed effect model using Gaussian processes: a personalized and reliable prediction for healthcare
  Ingyo Chung, Saehoon Kim, Juho Lee, Sung Ju Hwang, Eunho Yang
  AAAI 2020

• Beyond the Chinese restaurant and Pitman-Yor processes: statistical models with double power-law behavior
  Fadhel Ayed*, Juho Lee*, and François Caron
  (*: equal contribution)
  ICML 2019 (long oral presentation)

• Set transformer: a framework for attention-based permutation-invariant neural networks
  Juho Lee, Yoonho Lee, Jungtaek Kim, Adam R. Kosiorek, Seungjin Choi, and Yee Whye Teh
  Code
  ICML 2019

• Learning to propagate labels: transductive propagation network for few-shot learning
  Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang and Yi Yang
  ICLR 2019

• A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure
  Juho Lee, Lancelot F. James, Seungjin Choi, and François Caron
  AISTATS 2019 (oral presentation)
  Code

• Uncertainty-aware attention for reliable interpretation and prediction
  Jay Heo*, Hae Beom Lee*, Saehoon Kim, Juho Lee, Kwang Joon Kim, Eunho Yang, and Sung Ju Hwang
  (*: Equal Constribution)
  NeurIPS 2018

• Dropmax: adaptive variational softmax
  Hae Beom Lee, Juho Lee, Saehoon Kim, Eunho Yang, and Sung Ju Hwang
  NeurIPS 2018
  Code

• Bayesian inference on random simple graphs with power law degree distributions
  Juho Lee, Creighton Heakulani, Zoubin Ghahramani, Lancelot F. James, and Seingjin Choi
  ICML 2017
  Code

• Finite-dimensional BFRY priors and variational Bayesian inference for power law models
  Juho Lee, Lancelot F. James, and Seungjin Choi
  NIPS 2016

• Tree-guided MCMC inference for normalized random measure mixture models
  Juho Lee and Seungjin choi
  NIPS 2015
  Code

• Bayesian hierarchical clustering with exponential family: small-variance asymptotics and reducibility
  Juho Lee and Seungjin Choi
  AISTATS 2015

• Incremental tree-based inference with dependent normalized random measures
  Juho Lee and Seungjin Choi
  AISTATS 2014

• Online video segmentation by Bayesian split-merge clustering
  Juho Lee, Suha Kwak, Bohyung Han, and Seungjin Choi
  ECCV 2012

Workshops

• Early exiting for accelerated inference in diffusion models
  Taehong Moon, Moonseok Choi, EungGu Yun, Jongmin Yoon, Gayoung Lee, Juho Lee
  ICML 2023 workshop on Structured Probabilistic Inference & Generative Modeling, 2023

• Function space Bayesian pseudocoreset for Bayesian neural networks
  Balhae Kim, Hyungi Lee, Juho Lee
  ICML 2023 workshop on Structured Probabilistic Inference & Generative Modeling, 2023

• Towards safe self-distillation of internet-scale text-to-image diffusion models
  Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee
  ICML 2023 Workshop on Challenges in Deployable Generative AI, 2023

• Modeling uplift from observational time-series in continual scenarios
  Sanghyun Kim, Jungwon Choi, NamHee Kim, Jaesung Ryu, Juho Lee
  AAAI23 Bridge on Continual Casality (oral presentation), 2023

• Fine-tuning diffusion models with limited data
  Taehong Moon, Moonseok Choi, Gayoung Lee, Jung-Woo Ha, Juho Lee
  NeurIPS 2022 Workshop on Score-Based Methods, 2022

• Adaptive strategy for resetting a non-stationary Markov chain during learning via joint stochastic optimization
  Hyunsu Kim, Juho Lee, Hongseok Yang
  Third Symposium on Advances in Approximate Bayesian Inference, 2021

• Towards deep amortized clustering
  Juho Lee, Yoonho Lee, Yee Whye Teh
  NeurIPS 2019 Sets & Partitions workshop (contributed talk), 2019

• Graph embedding VAE: a permutation invariant model of graph structure
  Tony Duan, Juho Lee
  NeurIPS 2019 Graph Representation Learning workshop, 2019