Federated Continual Learning with Weighted Inter-client Transfer

ICML 2020 workshop in Lifelong Learning Federated Continual Learning with Weighted Inter-client Transfer Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang  There has been a surge of interest in continual learning and federated learning, both of which are importa...

Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation

EMNLP 2020 Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation Minki Kang, Moonsu Han, Sung Ju Hwang  We propose a method to automatically generate a domain- and task-adaptive maskings of the given text for self-supervised pr...

Neural Complexity Measures

NeurIPS 2020 Neural Complexity Measures Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi  While various complexity measures for diverse model classes have been proposed, specifying an appropriate measure capable of predicting and explaining generalization in deep ne...

MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures

NeurIPS 2020 MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures Jeongun Ryu, Jaewoong Shin, Hae Beom Lee, Sung Ju Hwang  Regularization and transfer learning are two popular techniques to enhance generalization on unseen data, which is a fun...

Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs

INTERSPEECH 2020 Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs Seong Min Kye, Youngmoon Jung, Hae Beom Lee, Sung Ju Hwang, Hoirin Kim  In practical settings, a speaker recognition system needs to identify a speaker given a short utter...

Meta Variance Transfer: Learning to Augment from The Others

ICML 2020 Meta Variance Transfer: Learning to Augment from The Others SeongJin Park, Seungju Han, Jiwon Baek, Insoo Kim, Juhwan Song, Hae Beom Lee, Jae-Joon Han, Sung Ju Hwang  Humans have the ability to robustly recognize objects with various factors of variations such as n...

Meta Dropout: Learning to Perturb Latent Features for Generalization

ICLR 2020 Meta Dropout: Learning to Perturb Latent Features for Generalization Hae Beom Lee, Taewook Nam, Eunho Yang, Sung Ju Hwang  A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb tra...

Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

NeurIPS 2020 Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction Jinheon Baek, Dong Bok Lee, Sung Ju Hwang  Many practical graph problems, such as knowledge graph construction and drug-to-drug interaction, require to handle multi-relati...

Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks

ICLR 2020 Learning to Balance: Bayesian Meta-Learning forImbalanced and Out-of-distribution Tasks Hae Beom Lee, Hayeon Lee, Donghyun Na, Saehoon Kim, Minseop Park, Eunho Yang, Sung Ju Hwang  While tasks could come with varying the number of instances and classes in realistic sett...

Federated Semi-Supervised Learning with Inter-Client Consistency

ICML 2020 (Workshop in Federated Learning) Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning Wonyong Jeong, Jaehong Yoon, Eunho Yang, Sung Ju Hwang  While existing federated learning approaches mostly require that clients have fully-labeled ...