277 citations · 1.6k across the 56 of their papers we have counts for
18 papers · 1 filter
Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models
Jaewoong Lee, Sangwon Jang, Jaehyeong Jo +5
Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performanc…
Dataset Condensation via Efficient Synthetic-Data Parameterization
Jang-Hyun Kim, Jinuk Kim, Seong Joon Oh +5
The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning. Recent studies on dataset condens…
Deformable Graph Transformer
Jinyoung Park, Seongjun Yun, Hyeonjin Park +5
Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the succes…
Metropolis-Hastings Data Augmentation for Graph Neural Networks
Hyeonjin Park, Seunghun Lee, Sihyeon Kim +5
Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a…
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference
Hyunseo Koh, Dahyun Kim, Jung-Woo Ha +1
Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual…
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
Dasol Hwang, Jinyoung Park, Sunyoung Kwon +3
In recent years, graph neural networks (GNNs) have been widely adopted in the representation learning of graph-structured data and provided state-of-the-art performance in various…
Which Strategies Matter for Noisy Label Classification? Insight into Loss and Uncertainty
Wonyoung Shin, Jung-Woo Ha, Shengzhe Li +3
Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have e…
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
Dasol Hwang, Jinyoung Park, Sunyoung Kwon +3
Graph neural networks have shown superior performance in a wide range of applications providing a powerful representation of graph-structured data. Recent works show that the repre…
Graphs, Entities, and Step Mixture
Kyuyong Shin, Wonyoung Shin, Jung-Woo Ha +1
Existing approaches for graph neural networks commonly suffer from the oversmoothing issue, regardless of how neighborhoods are aggregated. Most methods also focus on transductive…
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
Byeongho Heo, Sanghyuk Chun, Seong Joon Oh +5
Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the norm…
ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers
Jung-Woo Ha, Kihyun Nam, Jingu Kang +11
Automatic speech recognition (ASR) via call is essential for various applications, including AI for contact center (AICC) services. Despite the advancement of ASR, however, most pu…
Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
YoungJoon Yoo, Sanghyuk Chun, Sangdoo Yun +2
We propose a generic confidence-based approximation that can be plugged in and simplify the auto-regressive generation process with a proved convergence. We first assume that the p…
Which Ads to Show? Advertisement Image Assessment with Auxiliary Information via Multi-step Modality Fusion
Kyung-Wha Park, JungHoon Lee, Sunyoung Kwon +3
Assessing aesthetic preference is a fundamental task related to human cognition. It can also contribute to various practical applications such as image creation for online advertis…
CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms
Jinwoong Kim, Minkyu Kim, Heungseok Park +6
Many hyperparameter optimization (HyperOpt) methods assume restricted computing resources and mainly focus on enhancing performance. Here we propose a novel cloud-based HyperOpt (C…
NSML: A Machine Learning Platform That Enables You to Focus on Your Models
Nako Sung, Minkyu Kim, Hyunwoo Jo +8
Machine learning libraries such as TensorFlow and PyTorch simplify model implementation. However, researchers are still required to perform a non-trivial amount of manual tasks suc…
Automatic Music Highlight Extraction using Convolutional Recurrent Attention Networks
Jung-Woo Ha, Adrian Kim, Chanju Kim +2
Music highlights are valuable contents for music services. Most methods focused on low-level signal features. We propose a method for extracting highlights using high-level feature…
Highrisk Prediction from Electronic Medical Records via Deep Attention Networks
You Jin Kim, Yun-Geun Lee, Jeong Whun Kim +3
Predicting highrisk vascular diseases is a significant issue in the medical domain. Most predicting methods predict the prognosis of patients from pathological and radiological mea…
Overcoming Catastrophic Forgetting by Incremental Moment Matching
Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun +2
Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose a method, i.e. incremental mom…