Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning

ICLR 2019 Learning to Propagate Labels: Transductive Propagation Network for Few-shot LearningYanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, Yi Yang The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a ...

InstaGAN: Instance-aware Image-to-Image Translation

ICLR 2019 InstaGAN: Instance-aware Image-to-ImageTranslation Sangwoo Mo, Minsu Cho, Jinwoo Shin  Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). However, previous meth...

Graph Embedding VAE: A Permutation Invariant Model of Graph Structure

NeurIPS 2019 Workshop on Graph Representation Learning Graph Embedding VAE: A Permutation Invariant Model of Graph StructureTony Duan and Juho Lee Generative models of graph structure have applications in biology and social sciences. The state of the art is GraphRNN, which decomposes ...

Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data

ACL 2019 Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming DataMoonsu Han, Minki Kang, Hyunwoo Jung, Sung Ju Hwang We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or v...

Deep Gaussian Processes for Weakly Supervised Learning: Tumor Mutation Burden (TMB) Prediction

NeurIPS 2019 Workshop on Bayesian Deep Learning  Deep Gaussian Processes for Weakly Supervised Learning: Tumor Mutation Burden (TMB) Prediction  Sunho Park, Hongming Xu, Tae Hyun Hwang, Saehoon Kim  Tumor mutation burden (TMB) is a quantitative measurement of ...

Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior

ICML 2019 (full oral presentation) Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior * Fadhel Ayed, * Juho Lee, François Caron (* indicates equal contribution)  Bayesian nonparametric approaches, in particular...

Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior

ICML 2019 (full oral presentation) Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior* Fadhel Ayed, * Juho Lee, François Caron (* indicates equal contribution) Bayesian nonparametric approaches, in particular the Pitman-Yor p...

A Deep Learning Model for Real-time Mortality Prediction in Critically ill Children

Critical Care 2019 A Deep Learning Model for Real-time Mortality Prediction in Critically ill Children* Soo Yeon Kim, * Saehoon Kim, Joongbum Cho, Young Suh Kim, In Suk Sol, Youngchul Sung, Inhyeok Cho, Minseop Park, Haerin Jang, Yoon Hee Kim, ** Kyung Won Kim and Myung Hyun Sohn ...

A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure

AISTATS 2019 (oral presentation) A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structureJuho Lee, Lancelot James, Seungjin Choi, François Caron We consider a non-projective class of inhomogeneous random graph models with interpreta...

Uncertainty-Aware Attention for Reliable Interpretation and Prediction

NeurIPS 2018 Uncertainty-Aware Attention for ReliableInterpretation and PredictionJay Heo, Haebeom Lee, Saehoon Kim, Juho Lee, Kwangjun Kim, Eunho Yang, Sung Ju Hwang Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. Howe...