Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks

ICML 2019 Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks Juho Lee, Yoonho Lee, Jungtaek Kim, Adam R. Kosiorek, Seungjin Choi, Yee Whye Teh  Many machine learning tasks such as multiple instance learning, 3D shape recognition, and ...

Robust Inference via Generative Classifiers for Handling Noisy Labels

ICML 2019 Robust Inference via Generative Classifiers for Handling Noisy Labels Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, Jinwoo Shin  Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern dee...

Reliable Estimation of Individual Treatment Effect with Causal Information Bottleneck

ICML 2019 Reliable Estimation of Individual Treatment Effect with Causal Information BottleneckSungyub Kim, Yongsu Baek, Sung Ju Hwang, Eunho Yang Estimating individual level treatment effects (ITE) from observational data is a challenging and important area in causal machine learning and ...

Learning What and Where to Transfer

ICML 2019 Learning What and Where to Transfer Yunhun Jang, Hankook Lee, Sung Ju Hwang, Jinwoo Shin  As the application of deep learning has expanded to real-world problems with insufficient volume of training data, transfer learning recently has gained much attention as means 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...

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

ICML 2018 MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot LearningBo Zhao, Xinwei Sun, Yanwei Fu, Yuan Yao, Yizhou Wang We propose the idea that the features consist of three orthogonal parts, namely sparse strong signals, den...

Deep Asymmetric Multi-task Feature Learning

ICML 2018 Deep Asymmetric Multi-task Feature LearningHae Beom Lee, Eunho Yang, Sung Ju Hwang We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen i...

Bucket Renormalization for Approximate Inference

ICML 2018 Bucket Renormalization for Approximate InferenceSungsoo Ahn, Michael Chertkov, Adrian Weller, Jinwoo Shin Probabilistic graphical models are a key tool in machine learning applications. Computing the partition function, i.e., normalizing constant, is a fundamental task of statist...

SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization

ICML 2017 SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model ParallelizationJuyoung Kim, YooKoon Park, Gunhee Kim, Sungju Hwang We propose a novel deep neural network that is both lightweight and effectively structured for model parallelization. Our ne...