517 citations · 789 across the 25 of their papers we have counts for
14 papers · 1 filter
Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing
Joonhyung Park, June Yong Yang, Jinwoo Shin +2
The Mixup scheme suggests mixing a pair of samples to create an augmented training sample and has gained considerable attention recently for improving the generalizability of neura…
DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
Taesik Gong, Yewon Kim, Adiba Orzikulova +4
Many applications utilize sensors in mobile devices and machine learning to provide novel services. However, various factors such as different users, devices, and environments impa…
Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning
Seanie Lee, Hae Beom Lee, Juho Lee +1
Multilingual models jointly pretrained on multiple languages have achieved remarkable performance on various multilingual downstream tasks. Moreover, models finetuned on a single m…
Online Hyperparameter Meta-Learning with Hypergradient Distillation
Hae Beom Lee, Hayeon Lee, Jaewoong Shin +3
Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization, which can be considered as hyperparameters. Although such hyperp…
Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss
Jung Hyun Lee, Jihun Yun, Sung Ju Hwang +1
Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices. Although recent st…
Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
Hayeon Lee, Eunyoung Hyung, Sung Ju Hwang
Despite the success of recent Neural Architecture Search (NAS) methods on various tasks which have shown to output networks that largely outperform human-designed networks, convent…
FedMix: Approximation of Mixup under Mean Augmented Federated Learning
Tehrim Yoon, Sumin Shin, Sung Ju Hwang +1
Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to stor…
Learning to Perturb Word Embeddings for Out-of-distribution QA
Seanie Lee, Minki Kang, Juho Lee +1
QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets.However, QA models do not generalize well to unseen data that fall…
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
Dongchan Min, Dong Bok Lee, Eunho Yang +1
With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For practical applicability, a TTS model shou…
Adversarial purification with Score-based generative models
Jongmin Yoon, Sung Ju Hwang, Juho Lee
While adversarial training is considered as a standard defense method against adversarial attacks for image classifiers, adversarial purification, which purifies attacked images in…
HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning
Hayeon Lee, Sewoong Lee, Song Chong +1
For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and en…
Online Coreset Selection for Rehearsal-based Continual Learning
Jaehong Yoon, Divyam Madaan, Eunho Yang +1
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 the data points can be more repres…
Consistency Regularization for Adversarial Robustness
Jihoon Tack, Sihyun Yu, Jongheon Jeong +3
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfittin…
Model-Augmented Q-learning
Youngmin Oh, Jinwoo Shin, Eunho Yang +1
In recent years, -learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation…