Author name cluster

Heeyoung Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Uncertainty Estimation by Flexible Evidential Deep Learning

Taeseong Yoon
Heeyoung Kim

Uncertainty quantification (UQ) is crucial for deploying machine learning models in high-stakes applications, where overconfident predictions can lead to serious consequences. An effective UQ method must balance computational efficiency with the ability to generalize across diverse scenarios. Evidential deep learning (EDL) achieves efficiency by modeling uncertainty through the prediction of a Dirichlet distribution over class probabilities. However, the restrictive assumption of Dirichlet-distributed class probabilities limits EDL's robustness, particularly in complex or unforeseen situations. To address this, we propose *flexible evidential deep learning* ($\mathcal{F}$-EDL), which extends EDL by predicting a flexible Dirichlet distribution—a generalization of the Dirichlet distribution—over class probabilities. This approach provides a more expressive and adaptive representation of uncertainty, significantly enhancing UQ generalization and reliability under challenging scenarios. We theoretically establish several advantages of $\mathcal{F}$-EDL and empirically demonstrate its state-of-the-art UQ performance across diverse evaluation settings, including classical, long-tailed, and noisy in-distribution scenarios.

PDF Details

ICML Conference 2024 Conference Paper

Uncertainty Estimation by Density Aware Evidential Deep Learning

Taeseong Yoon
Heeyoung Kim

Evidential deep learning (EDL) has shown remarkable success in uncertainty estimation. However, there is still room for improvement, particularly in out-of-distribution (OOD) detection and classification tasks. The limited OOD detection performance of EDL arises from its inability to reflect the distance between the testing example and training data when quantifying uncertainty, while its limited classification performance stems from its parameterization of the concentration parameters. To address these limitations, we propose a novel method called Density Aware Evidential Deep Learning (DAEDL). DAEDL integrates the feature space density of the testing example with the output of EDL during the prediction stage, while using a novel parameterization that resolves the issues in the conventional parameterization. We prove that DAEDL enjoys a number of favorable theoretical properties. DAEDL demonstrates state-of-the-art performance across diverse downstream tasks related to uncertainty estimation and classification.

Details

AAAI Conference 2023 Conference Paper

Inverse-Reference Priors for Fisher Regularization of Bayesian Neural Networks

Keunseo Kim
Eun-Yeol Ma
Jeongman Choi
Heeyoung Kim

Recent studies have shown that the generalization ability of deep neural networks (DNNs) is closely related to the Fisher information matrix (FIM) calculated during the early training phase. Several methods have been proposed to regularize the FIM for increased generalization of DNNs. However, they cannot be used directly for Bayesian neural networks (BNNs) because the variable parameters of BNNs make it difficult to calculate the FIM. To address this problem, we achieve regularization of the FIM of BNNs by specifying a new suitable prior distribution called the inverse-reference (IR) prior. To regularize the FIM, the IR prior is derived as the inverse of the reference prior that imposes minimal prior knowledge on the parameters and maximizes the trace of the FIM. We demonstrate that the IR prior can enhance the generalization ability of BNNs for large-scale data over previously used priors while providing adequate uncertainty quantifications using various benchmark image datasets and BNN structures.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning

Hyuck Lee
Seungjae Shin
Heeyoung Kim

Existing semi-supervised learning (SSL) algorithms typically assume class-balanced datasets, although the class distributions of many real world datasets are imbalanced. In general, classifiers trained on a class-imbalanced dataset are biased toward the majority classes. This issue becomes more problematic for SSL algorithms because they utilize the biased prediction of unlabeled data for training. However, traditional class-imbalanced learning techniques, which are designed for labeled data, cannot be readily combined with SSL algorithms. We propose a scalable class-imbalanced SSL algorithm that can effectively use unlabeled data, while mitigating class imbalance by introducing an auxiliary balanced classifier (ABC) of a single layer, which is attached to a representation layer of an existing SSL algorithm. The ABC is trained with a class-balanced loss of a minibatch, while using high-quality representations learned from all data points in the minibatch using the backbone SSL algorithm to avoid overfitting and information loss. Moreover, we use consistency regularization, a recent SSL technique for utilizing unlabeled data in a modified way, to train the ABC to be balanced among the classes by selecting unlabeled data with the same probability for each class. The proposed algorithm achieves state-of-the-art performance in various class-imbalanced SSL experiments using four benchmark datasets.

PDF Details

NeurIPS Conference 2021 Conference Paper

Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models

Keunseo Kim
JunCheol Shin
Heeyoung Kim

Several out-of-distribution (OOD) detection scores have been recently proposed for deep generative models because the direct use of the likelihood threshold for OOD detection has been shown to be problematic. In this paper, we propose a new OOD score based on a Bayesian hypothesis test called the locally most powerful Bayesian test (LMPBT). The LMPBT is locally most powerful in that the alternative hypothesis (the representative parameter for the OOD sample) is specified to maximize the probability that the Bayes factor exceeds the evidence threshold in favor of the alternative hypothesis provided that the parameter specified under the alternative hypothesis is in the neighborhood of the parameter specified under the null hypothesis. That is, under this neighborhood parameter condition, the test with the proposed alternative hypothesis maximizes the probability of correct detection of OOD samples. We also propose numerical strategies for more efficient and reliable computation of the LMPBT for practical application to deep generative models. Evaluations conducted of the OOD detection performance of the LMPBT on various benchmark datasets demonstrate its superior performance over existing OOD detection methods.

PDF Details

ICML Conference 2021 Conference Paper

Objective Bound Conditional Gaussian Process for Bayesian Optimization

Taewon Jeong
Heeyoung Kim

A Gaussian process is a standard surrogate model for an unknown objective function in Bayesian optimization. In this paper, we propose a new surrogate model, called the objective bound conditional Gaussian process (OBCGP), to condition a Gaussian process on a bound on the optimal function value. The bound is obtained and updated as the best observed value during the sequential optimization procedure. Unlike the standard Gaussian process, the OBCGP explicitly incorporates the existence of a point that improves the best known bound. We treat the location of such a point as a model parameter and estimate it jointly with other parameters by maximizing the likelihood using variational inference. Within the standard Bayesian optimization framework, the OBCGP can be combined with various acquisition functions to select the next query point. In particular, we derive cumulative regret bounds for the OBCGP combined with the upper confidence bound acquisition algorithm. Furthermore, the OBCGP can inherently incorporate a new type of prior knowledge, i. e. , the bounds on the optimum, if it is available. The incorporation of this type of prior knowledge into a surrogate model has not been studied previously. We demonstrate the effectiveness of the OBCGP through its application to Bayesian optimization tasks, such as the sequential design of experiments and hyperparameter optimization in neural networks.

Details

NeurIPS Conference 2020 Conference Paper

OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification

Taewon Jeong
Heeyoung Kim

We propose a few-shot learning method for detecting out-of-distribution (OOD) samples from classes that are unseen during training while classifying samples from seen classes using only a few labeled examples. For detecting unseen classes while generalizing to new samples of known classes, we synthesize fake samples, i. e. , OOD samples, but that resemble in-distribution samples, and use them along with real samples. Our approach is based on an extension of model-agnostic meta learning (MAML) and is denoted as OOD-MAML, which not only learns a model initialization but also the initial fake samples across tasks. The learned initial fake samples can be used to quickly adapt to new tasks to form task-specific fake samples with only one or a few gradient update steps using MAML. For testing, OOD-MAML converts a K-shot N-way classification task into N sub-tasks of K-shot OOD detection with respect to each class. The joint analysis of N sub-tasks facilitates simultaneous classification and OOD detection and, furthermore, offers an advantage, in that it does not require re-training when the number of classes for a test task differs from that for training tasks; it is sufficient to simply assume as many sub-tasks as the number of classes for the test task. We also demonstrate the effective performance of OOD-MAML over benchmark datasets.

PDF Details

ICML Conference 2019 Conference Paper

Ladder Capsule Network

Taewon Jeong
Youngmin Lee
Heeyoung Kim

We propose a new architecture of the capsule network called the ladder capsule network, which has an alternative building block to the dynamic routing algorithm in the capsule network (Sabour et al. , 2017). Motivated by the need for using only important capsules during training for robust performance, we first introduce a new layer called the pruning layer, which removes irrelevant capsules. Based on the selected capsules, we construct higher-level capsule outputs. Subsequently, to capture the part-whole spatial relationships, we introduce another new layer called the ladder layer, the outputs of which are regressed lower-level capsule outputs from higher-level capsules. Unlike the capsule network adopting the routing-by-agreement, the ladder capsule network uses backpropagation from a loss function to reconstruct the lower-level capsule outputs from higher-level capsules; thus, the ladder layer implements the reverse directional inference of the agreement/disagreement mechanism of the capsule network. The experiments on MNIST demonstrate that the ladder capsule network learns an equivariant representation and improves the capability to extrapolate or generalize to pose variations.

Details

IJCAI Conference 2016 Conference Paper

Bayesian Nonparametric Collaborative Topic Poisson Factorization for Electronic Health Records-Based Phenotyping

Wonsung Lee
Youngmin Lee
Heeyoung Kim
Il-Chul Moon

Phenotyping with electronic health records (EHR) has received much attention in recent years because the phenotyping opens a new way to discover clinically meaningful insights, such as disease progression and disease subtypes without human supervisions. In spite of its potential benefits, the complex nature of EHR often requires more sophisticated methodologies compared with traditional methods. Previous works on EHR-based phenotyping utilized unsupervised and supervised learning methods separately by independently detecting phenotypes and predicting medical risk scores. To improve EHR-based phenotyping by bridging the separated methods, we present Bayesian nonparametric collaborative topic Poisson factorization (BN-CTPF) that is the first nonparametric content-based Poisson factorization and first application of jointly analyzing the phenotye topics and estimating the individual risk scores. BN-CTPF shows better performances in predicting the risk scores when we compared the model with previous matrix factorization and topic modeling methods including a Poisson factorization and its collaborative extensions. Also, BN-CTPF provides faceted views on the phenotype topics by patients' demographics. Finally, we demonstrate a scalable stochastic variational inference algorithm by applying BN-CTPF to a national-scale EHR dataset.

PDF Details

IS Journal 2016 Journal Article

Ordinal Classification of Imbalanced Data with Application in Emergency and Disaster Information Services

Sungil Kim
Heeyoung Kim
Younghwan Namkoong

Previous ordinal classification methods implicitly assume that the class distribution within a dataset is balanced, which is often not the case for real-world datasets. If the dataset is imbalanced, the previous methods tend to be biased toward the majority class. The authors propose a new method for ordinal classification that attempts to mitigate the impact of imbalanced datasets. They propose a modified version of the weighted k-nearest neighbors method that determines the class membership using the Î±th quantile of the estimated class probability distribution and thus mitigates the impact of the class imbalance.

Details DOI