16 citations · 105 across the 22 of their papers we have counts for
25 papers
Loss-Curvature Matching for Dataset Selection and Condensation
Seungjae Shin, Heesun Bae, Donghyeok Shin +2
Training neural networks on a large dataset requires substantial computational costs. Dataset reduction selects or synthesizes data instances based on the large dataset, while mini…
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
Dongjun Kim, Yeongmin Kim, Se Jung Kwon +2
The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervis…
Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
JoonHo Jang, Byeonghu Na, DongHyeok Shin +3
Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain. Existing domain adversarial learning methods a…
From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model
HeeSun Bae, Seungjae Shin, Byeonghu Na +3
Noisy labels are inevitable yet problematic in machine learning society. It ruins the generalization of a classifier by making the classifier over-fitted to noisy labels. Existing…
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
Dongjun Kim, Byeonghu Na, Se Jung Kwon +3
Whereas diverse variations of diffusion models exist, extending the linear diffusion into a nonlinear diffusion process is investigated by very few works. The nonlinearity effect h…
Automatic Calibration Framework of Agent-Based Models for Dynamic and Heterogeneous Parameters
Dongjun Kim, Tae-Sub Yun, Il-Chul Moon +1
Agent-based models (ABMs) highlight the importance of simulation validation, such as qualitative face validation and quantitative empirical validation. In particular, we focused on…
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
Dongjun Kim, Seungjae Shin, Kyungwoo Song +2
Recent advances in diffusion models bring state-of-the-art performance on image generation tasks. However, empirical results from previous research in diffusion models imply an inv…
Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
Mingi Ji, Seungjae Shin, Seunghyun Hwang +2
Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher networ…
Neural Posterior Regularization for Likelihood-Free Inference
Dongjun Kim, Kyungwoo Song, Seungjae Shin +3
A simulation is useful when the phenomenon of interest is either expensive to regenerate or irreproducible with the same context. Recently, Bayesian inference on the distribution o…
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder
Hyemi Kim, Seungjae Shin, JoonHo Jang +4
The problem of fair classification can be mollified if we develop a method to remove the embedded sensitive information from the classification features. This line of separating th…
LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning
Yoon-Yeong Kim, Kyungwoo Song, JoonHo Jang +1
Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high. Besides active learning,…
Sequential Likelihood-Free Inference with Neural Proposal
Dongjun Kim, Kyungwoo Song, YoonYeong Kim +4
Bayesian inference without the likelihood evaluation, or likelihood-free inference, has been a key research topic in simulation studies for gaining quantitatively validated simulat…
Implicit Kernel Attention
Kyungwoo Song, Yohan Jung, Dongjun Kim +1
\textit{Attention} computes the dependency between representations, and it encourages the model to focus on the important selective features. Attention-based models, such as Transf…
Adversarial Likelihood-Free Inference on Black-Box Generator
Dongjun Kim, Weonyoung Joo, Seungjae Shin +2
Generative Adversarial Network (GAN) can be viewed as an implicit estimator of a data distribution, and this perspective motivates using the adversarial concept in the true input p…
Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation
Seungjae Shin, Kyungwoo Song, JoonHo Jang +3
Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discrimi…
Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables
Weonyoung Joo, Dongjun Kim, Seungjae Shin +1
Estimating the gradients of stochastic nodes in stochastic computational graphs is one of the crucial research questions in the deep generative modeling community, which enables th…
Sequential Recommendation with Relation-Aware Kernelized Self-Attention
Mingi Ji, Weonyoung Joo, Kyungwoo Song +2
Recent studies identified that sequential Recommendation is improved by the attention mechanism. By following this development, we propose Relation-Aware Kernelized Self-Attention…
Automatic Calibration of Dynamic and Heterogeneous Parameters in Agent-based Model
Dongjun Kim, Tae-Sub Yun, Il-Chul Moon
While simulations have been utilized in diverse domains, such as urban growth modeling, market dynamics modeling, etc; some of these applications may require validations based upon…
Bivariate Beta-LSTM
Kyungwoo Song, JoonHo Jang, Seung jae Shin +1
Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in…
Hierarchical Context enabled Recurrent Neural Network for Recommendation
Kyungwoo Song, Mingi Ji, Sungrae Park +1
A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the tran…
Neural Ideal Point Estimation Network
Kyungwoo Song, Wonsung Lee, Il-Chul Moon
Understanding politics is challenging because the politics take the influence from everything. Even we limit ourselves to the political context in the legislative processes; we nee…
Adversarial Dropout for Recurrent Neural Networks
Sungrae Park, Kyungwoo Song, Mingi Ji +2
Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques…
Dirichlet Variational Autoencoder
Weonyoung Joo, Wonsung Lee, Sungrae Park +1
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabil…
Hierarchically Clustered Representation Learning
Su-Jin Shin, Kyungwoo Song, Il-Chul Moon
The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with rep…