Search Results for author: Il-Chul Moon

Found 37 papers, 23 papers with code

Unknown Domain Inconsistency Minimization for Domain Generalization

no code implementations12 Mar 2024 Seungjae Shin, HeeSun Bae, Byeonghu Na, Yoon-Yeong Kim, Il-Chul Moon

In particular, by aligning the loss landscape acquired in the source domain to the loss landscape of perturbed domains, we expect to achieve generalization grounded on these flat minima for the unknown domains.

Domain Generalization

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning

1 code implementation5 Mar 2024 HeeSun Bae, Seungjae Shin, Byeonghu Na, Il-Chul Moon

We propose good utilization of the transition matrix is crucial and suggest a new utilization method based on resampling, coined RENT.

Learning with noisy labels

Training Unbiased Diffusion Models From Biased Dataset

1 code implementation2 Mar 2024 Yeongmin Kim, Byeonghu Na, Minsang Park, JoonHo Jang, Dongjun Kim, Wanmo Kang, Il-Chul Moon

While directly applying it to score-matching is intractable, we discover that using the time-dependent density ratio both for reweighting and score correction can lead to a tractable form of the objective function to regenerate the unbiased data density.

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

1 code implementation2 Mar 2024 Hyungho Na, Yunkyeong Seo, Il-Chul Moon

To address this, we introduce Efficient episodic Memory Utilization (EMU) for MARL, with two primary objectives: (a) accelerating reinforcement learning by leveraging semantically coherent memory from an episodic buffer and (b) selectively promoting desirable transitions to prevent local convergence.

Multi-agent Reinforcement Learning Q-Learning +3

Label-Noise Robust Diffusion Models

1 code implementation27 Feb 2024 Byeonghu Na, Yeongmin Kim, HeeSun Bae, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, Il-Chul Moon

This paper proposes Transition-aware weighted Denoising Score Matching (TDSM) for training conditional diffusion models with noisy labels, which is the first study in the line of diffusion models.

Denoising

Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior

1 code implementation9 Jan 2024 Youngjae Cho, HeeSun Bae, Seungjae Shin, Yeo Dong Youn, Weonyoung Joo, Il-Chul Moon

This paper presents a Bayesian-based framework of prompt learning, which could alleviate the overfitting issues on few-shot learning application and increase the adaptability of prompts on unseen instances.

Few-Shot Learning Prompt Engineering

Frequency Domain-based Dataset Distillation

1 code implementation NeurIPS 2023 DongHyeok Shin, Seungjae Shin, Il-Chul Moon

This paper presents FreD, a novel parameterization method for dataset distillation, which utilizes the frequency domain to distill a small-sized synthetic dataset from a large-sized original dataset.

Loss-Curvature Matching for Dataset Selection and Condensation

1 code implementation8 Mar 2023 Seungjae Shin, HeeSun Bae, DongHyeok Shin, Weonyoung Joo, Il-Chul Moon

Training neural networks on a large dataset requires substantial computational costs.

SAAL: Sharpness-Aware Active Learning

1 code implementation Proceedings of the 40th International Conference on Machine Learning 2023 Yoon-Yeong Kim, Youngjae Cho, JoonHo Jang, Byeonghu Na, Yeongmin Kim, Kyungwoo Song, Wanmo Kang, Il-Chul Moon

Specifically, our proposed method, Sharpness-Aware Active Learning (SAAL), constructs its acquisition function by selecting unlabeled instances whose perturbed loss becomes maximum.

Active Learning Image Classification +3

Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation

1 code implementation15 Jun 2022 JoonHo Jang, Byeonghu Na, DongHyeok Shin, Mingi Ji, Kyungwoo Song, Il-Chul Moon

Therefore, we propose Unknown-Aware Domain Adversarial Learning (UADAL), which $\textit{aligns}$ the source and the target-$\textit{known}$ distribution while simultaneously $\textit{segregating}$ the target-$\textit{unknown}$ distribution in the feature alignment procedure.

Domain Adaptation

Maximum Likelihood Training of Implicit Nonlinear Diffusion Models

1 code implementation27 May 2022 Dongjun Kim, Byeonghu Na, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, Il-Chul Moon

Whereas diverse variations of diffusion models exist, extending the linear diffusion into a nonlinear diffusion process is investigated by very few works.

Image Generation

Automatic Calibration Framework of Agent-Based Models for Dynamic and Heterogeneous Parameters

no code implementations7 Mar 2022 Dongjun Kim, Tae-Sub Yun, Il-Chul Moon, Jang Won Bae

Agent-based models (ABMs) highlight the importance of simulation validation, such as qualitative face validation and quantitative empirical validation.

Maximum Likelihood Training of Parametrized Diffusion Model

no code implementations29 Sep 2021 Dongjun Kim, Byeonghu Na, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, Il-Chul Moon

Specifically, PDM utilizes the flow to non-linearly transform a data variable into a latent variable, and PDM applies the diffusion process to the transformed latent distribution with the linear diffusing mechanism.

Image Generation

High Precision Score-based Diffusion Models

no code implementations29 Sep 2021 Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon

From the theory side, the difficulty arises in estimating the high precision diffusion because the data score goes to $\infty$ as $t \rightarrow 0$ of the diffusion time.

Image Generation Vocal Bursts Intensity Prediction

Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation

1 code implementation10 Jun 2021 Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon

This paper investigates with sufficient empirical evidence that such inverse correlation happens because density estimation is significantly contributed by small diffusion time, whereas sample generation mainly depends on large diffusion time.

Ranked #2 on Image Generation on CIFAR-10 (Inception score metric)

Density Estimation Image Generation

LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning

1 code implementation NeurIPS 2021 Yooon-Yeong Kim, Kyungwoo Song, JoonHo Jang, Il-Chul Moon

Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high.

Active Learning Data Augmentation +1

Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation

1 code implementation CVPR 2021 Mingi Ji, Seungjae Shin, Seunghyun Hwang, Gibeom Park, Il-Chul Moon

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 network at the deployment stage.

Data Augmentation object-detection +4

Neural Posterior Regularization for Likelihood-Free Inference

1 code implementation15 Feb 2021 Dongjun Kim, Kyungwoo Song, Seungjae Shin, Wanmo Kang, Il-Chul Moon, Weonyoung Joo

A simulation is useful when the phenomenon of interest is either expensive to regenerate or irreproducible with the same context.

Bayesian Inference

Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder

no code implementations24 Nov 2020 Hyemi Kim, Seungjae Shin, JoonHo Jang, Kyungwoo Song, Weonyoung Joo, Wanmo Kang, Il-Chul Moon

Therefore, this paper proposes Disentangled Causal Effect Variational Autoencoder (DCEVAE) to resolve this limitation by disentangling the exogenous uncertainty into two latent variables: either 1) independent to interventions or 2) correlated to interventions without causality.

Attribute Causal Inference +3

LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning

no code implementations NeurIPS 2021 Yoon-Yeong Kim, Kyungwoo Song, JoonHo Jang, Il-Chul Moon

Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high.

Active Learning Data Augmentation +1

Neutralizing Gender Bias in Word Embeddings with Latent Disentanglement and Counterfactual Generation

no code implementations Findings of the Association for Computational Linguistics 2020 Seungjae Shin, Kyungwoo Song, JoonHo Jang, Hyemi Kim, Weonyoung Joo, Il-Chul Moon

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 discriminative results from the various downstream tasks.

counterfactual Disentanglement +1

Sequential Likelihood-Free Inference with Neural Proposal

1 code implementation15 Oct 2020 Dongjun Kim, Kyungwoo Song, YoonYeong Kim, Yongjin Shin, Wanmo Kang, Il-Chul Moon, Weonyoung Joo

This paper introduces a new sampling approach, called Neural Proposal (NP), of the simulation input that resolves the biased data collection as it guarantees the i. i. d.

Bayesian Inference

Implicit Kernel Attention

no code implementations11 Jun 2020 Kyungwoo Song, Yohan Jung, Dongjun Kim, Il-Chul Moon

For the attention in Transformer and GAT, we derive that the attention is a product of two parts: 1) the RBF kernel to measure the similarity of two instances and 2) the exponential of $L^{2}$ norm to compute the importance of individual instances.

Graph Attention Node Classification +2

Adversarial Likelihood-Free Inference on Black-Box Generator

no code implementations13 Apr 2020 Dongjun Kim, Weonyoung Joo, Seungjae Shin, Kyungwoo Song, Il-Chul Moon

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 parameter estimation of black-box generators.

Generative Adversarial Network

Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation

no code implementations7 Apr 2020 Seungjae Shin, Kyungwoo Song, JoonHo Jang, Hyemi Kim, Weonyoung Joo, Il-Chul Moon

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 discriminative results from the various downstream tasks.

counterfactual Disentanglement +2

Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables

no code implementations4 Mar 2020 Weonyoung Joo, Dongjun Kim, Seungjae Shin, Il-Chul Moon

Stochastic gradient estimators of discrete random variables are widely explored, for example, Gumbel-Softmax reparameterization trick for Bernoulli and categorical distributions.

Topic Models

Sequential Recommendation with Relation-Aware Kernelized Self-Attention

no code implementations15 Nov 2019 Mingi Ji, Weonyoung Joo, Kyungwoo Song, Yoon-Yeong Kim, Il-Chul Moon

This work merges the self-attention of the Transformer and the sequential recommendation by adding a probabilistic model of the recommendation task specifics.

Relation Sequential Recommendation

Automatic Calibration of Dynamic and Heterogeneous Parameters in Agent-based Model

no code implementations9 Aug 2019 Dongjun Kim, Tae-Sub Yun, Il-Chul Moon

While this parameter calibration has been fixed throughout a simulation execution, this paper expands the static parameter calibration in two dimensions: dynamic calibration and heterogeneous calibration.

Bivariate Beta-LSTM

1 code implementation25 May 2019 Kyungwoo Song, JoonHo Jang, Seung jae Shin, Il-Chul Moon

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 [0, 1] through a sigmoid function.

Density Estimation General Classification +5

Neural Ideal Point Estimation Network

1 code implementation26 Apr 2019 Kyungwoo Song, Wonsung Lee, Il-Chul Moon

Understanding politics is challenging because the politics take the influence from everything.

Hierarchical Context enabled Recurrent Neural Network for Recommendation

1 code implementation26 Apr 2019 Kyungwoo Song, Mingi Ji, Sungrae Park, Il-Chul Moon

The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests.

Sequential Recommendation

Adversarial Dropout for Recurrent Neural Networks

2 code implementations22 Apr 2019 Sungrae Park, Kyungwoo Song, Mingi Ji, Wonsung Lee, Il-Chul Moon

Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs).

Language Modelling Semi-Supervised Text Classification

Hierarchically Clustered Representation Learning

no code implementations ICLR 2019 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.

Clustering Representation Learning

Dirichlet Variational Autoencoder

1 code implementation ICLR 2019 Weonyoung Joo, Wonsung Lee, Sungrae Park, Il-Chul Moon

The experimental results show that 1) DirVAE models the latent representation result with the best log-likelihood compared to the baselines; and 2) DirVAE produces more interpretable latent values with no collapsing issues which the baseline models suffer from.

General Classification Topic Models

Adversarial Dropout for Supervised and Semi-supervised Learning

3 code implementations12 Jul 2017 Sungrae Park, Jun-Keon Park, Su-Jin Shin, Il-Chul Moon

Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.