Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning

ICLR 2022 Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning Seanie Lee, Hae Beom Lee, Juho Lee, Sung Ju Hwang  Multilingual models jointly pretrained on multiple languages have achieved remarkable performance on various multilingual downstream tasks. Mor...

Rethinking the Representational Continuity: Towards Unsupervised Continual Learning

ICLR 2022 Rethinking the Representational Continuity: Towards Unsupervised Continual Learning Divyam Madaan, Jaehong Yoon, Yuanchun Li, Yunxin Liu, Sung Ju Hwang  Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. ...

Online Hyperparameter Meta-Learning with Hypergradient Distillation

ICLR 2022 Online Hyperparameter Meta-Learning with Hypergradient Distillation Hae Beom Lee, Hayeon Lee, Jaewoong Shin, Eunho Yang, Timothy Hospedales, Sung Ju Hwang    Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optim...

Online Coreset Selection for Rehearsal-based Continual Learning

ICLR 2022 Online Coreset Selection for Rehearsal-based Continual Learning Jaehong Yoon, Divyam Madaan, Eunho Yang, Sung Ju Hwang  A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of...

Model-augmented Prioritized Experience Replay

ICLR 2022 Model-augmented Prioritized Experience Replay Youngmin Oh, Jinwoo Shin, Eunho Yang, Sung Ju Hwang    Experience replay is an essential component in off-policy model-free reinforcement learning (MfRL). Due to its effectiveness, various methods for calculating priori...

Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty

ICLR 2022 Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty Jeffrey Ryan Willette, Hae Beom Lee, Juho Lee, Sung Ju Hwang  Numerous recent works utilize bi-Lipschitz regularization of neural network layers to preserve relative distances between d...

GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification

ICLR 2022 GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification Joonhyung Park*, Jaeyun Song*, Eunho Yang (*: equal contribution)  In many real-world node classification scenarios, nodes are highly class-imbalanced, where graph neural networks (G...

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets

ICLR 2021 Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets Hayeon Lee, Eunyoung Hyung and Sung Ju Hwang  Despite the success of recent Neural Architecture Search (NAS) methods on various tasks which have shown to output networks that largely outperfo...

Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning

ICLR 2021 Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning Dong Bok Lee, Dongchan Min, Seanie Lee and Sung Ju Hwang  Unsupervised learning aims to learn meaningful representations from unlabeled data which can captures its intrinsic structure, that can be transf...

Learning to Sample with Local and Global Contexts in Experience Replay Buffers

ICLR 2021 Learning to Sample with Local and Global Contexts in Experience Replay Buffers Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang, Sung Ju Hwang  Experience replay, which enables the agents to remember and reuse experience from the past, has played a significant role in th...