Author name cluster

Minseok 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

AAAI Conference 2026 Conference Paper

Physics-Informed Approach for Exploratory Hamilton–Jacobi–Bellman Equations via Policy Iterations

Yeongjong Kim
Namkyeong Cho
Minseok Kim
Yeoneung Kim

We propose a mesh-free policy iteration framework based on physics-informed neural networks (PINNs) for solving entropy-regularized stochastic control problems. The method iteratively alternates between soft policy evaluation and improvement using automatic differentiation and neural approximation, without relying on spatial discretization. We present a detailed error analysis that decomposes the total approximation error into three sources: iteration error, policy network error, and PDE residual error. The proposed algorithm is validated with a range of challenging control tasks, including high-dimensional linear-quadratic regulation in 5D and 10D, as well as nonlinear systems such as pendulum and cartpole problems. Numerical results confirm the scalability, accuracy, and robustness of our approach across both linear and nonlinear benchmarks.

PDF Details DOI

JBHI Journal 2025 Journal Article

Adaptive Metadata-Guided Supervised Contrastive Learning for Domain Adaptation on Respiratory Sound Classification

June-Woo Kim
Miika Toikkanen
Amin Jalali
Minseok Kim
Hye-Ji Han
Hyunwoo Kim
Wonwoo Shin
Ho-Young Jung

Despite considerable advancements in deep learning, optimizing respiratory sound classification (RSC) models remains challenging. This is partly due to the bias from inconsistent respiratory sound recording processes and imbalanced representation of demographics, which leads to poor performance when a model trained with the dataset is applied to real-world use cases. RSC datasets usually include various metadata attributes describing certain aspects of the data, such as environmental and demographic factors. To address the issues caused by bias, we take advantage of the metadata provided by RSC datasets and explore approaches for metadata-guided domain adaptation. We thoroughly evaluate the effect of various metadata attributes and their combinations on a simple metadata-guided approach, but also introduce a more advanced method that adaptively rescales the suitable metadata combinations to improve domain adaptation during training. The findings indicate a robust reduction in domain dependency and improvement in detection accuracy on both ICBHI and our own dataset. Specifically, the implementation of our proposed methods led to an improved score of 84. 97%, which signifies a substantial enhancement of 7. 37% compared to the baseline model.

Details DOI

AAAI Conference 2024 Conference Paper

Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise

Hwanjun Song
Minseok Kim
Jae-Gil Lee

Multi-label classification poses challenges due to imbalanced and noisy labels in training data. In this paper, we propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced labels, generating minority-augmented instances with high diversity. It also refines multi-labels at the label-wise granularity, categorizing noisy labels as clean, re-labeled, or ambiguous for robust optimization. Extensive experiments on three benchmark datasets demonstrate that BalanceMix outperforms existing state-of-the-art methods. We release the code at https://github.com/DISL-Lab/BalanceMix.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Pose-Guided 3D Human Generation in Indoor Scene

Minseok Kim
Changwoo Kang
Jeongin Park
Kyungdon Joo

In this work, we address the problem of scene-aware 3D human avatar generation based on human-scene interactions. In particular, we pay attention to the fact that physical contact between a 3D human and a scene (i.e., physical human-scene interactions) requires a geometrical alignment to generate natural 3D human avatar. Motivated by this fact, we present a new 3D human generation framework that considers geometric alignment on potential contact areas between 3D human avatars and their surroundings. In addition, we introduce a compact yet effective human pose classifier that classifies the human pose and provides potential contact areas of the 3D human avatar. It allows us to adaptively use geometric alignment loss according to the classified human pose. Compared to state-of-the-art method, our method can generate physically and semantically plausible 3D humans that interact naturally with 3D scenes without additional post-processing. In our evaluations, we achieve the improvements with more plausible interactions and more variety of poses than prior research in qualitative and quantitative analysis. Project page: https://bupyeonghealer.github.io/phin/.

PDF Details DOI

AAAI Conference 2022 Conference Paper

COVID-EENet: Predicting Fine-Grained Impact of COVID-19 on Local Economies

Doyoung Kim
Hyangsuk Min
Youngeun Nam
Hwanjun Song
Susik Yoon
Minseok Kim
Jae-Gil Lee

Assessing the impact of the COVID-19 crisis on economies is fundamental to tailor the responses of the governments to recover from the crisis. In this paper, we present a novel approach to assessing the economic impact with a large-scale credit card transaction dataset at a fine granularity. For this purpose, we develop a fine-grained economicepidemiological modeling framework COVID-EENet, which is featured with a two-level deep neural network. In support of the fine-grained EEM, COVID-EENet learns the impact of nearby mass infection cases on the changes of local economies in each district. Through the experiments using the nationwide dataset, given a set of active mass infection cases, COVID-EENet is shown to precisely predict the sales changes in two or four weeks for each district and business category. Therefore, policymakers can be informed of the predictive impact to put in the most effective mitigation measures. Overall, we believe that our work opens a new perspective of using financial data to recover from the economic crisis. For public use in this urgent problem, we release the source code at https: //github. com/kaist-dmlab/COVID-EENet.

PDF Details

AAAI Conference 2022 Conference Paper

Meta-Learning for Online Update of Recommender Systems

Minseok Kim
Hwanjun Song
Yooju Shin
Dongmin Park
Kijung Shin
Jae-Gil Lee

Online recommender systems should be always aligned with users’ current interest to accurately suggest items that each user would like. Since user interest usually evolves over time, the update strategy should be flexible to quickly catch users’ current interest from continuously generated new user-item interactions. Existing update strategies focus either on the importance of each user-item interaction or the learning rate for each recommender parameter, but such one-directional flexibility is insufficient to adapt to varying relationships between interactions and parameters. In this paper, we propose MeLON, a meta-learning based novel online recommender update strategy that supports two-directional flexibility. It is featured with an adaptive learning rate for each parameterinteraction pair for inducing a recommender to quickly learn users’ up-to-date interest. The procedure of MeLON is optimized following a meta-learning approach: it learns how a recommender learns to generate the optimal learning rates for future updates. Specifically, MeLON first enriches the meaning of each interaction based on previous interactions and identifies the role of each parameter for the interaction; and then combines these two pieces of information to generate an adaptive learning rate. Theoretical analysis and extensive evaluation on three real-world online recommender datasets validate the effectiveness of MeLON.

PDF Details

AAAI Conference 2021 Conference Paper

PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest Recommendation

Minseok Kim
Hwanjun Song
Doyoung Kim
Kijung Shin
Jae-Gil Lee

Point-of-interest (POI) recommendation has become an important research topic in these days. The user check-in history used as the input to POI recommendation is very imbalanced and noisy because of sparse and missing check-ins. Although sample reweighting is commonly adopted for addressing this challenge with the input data, its fixed weighting scheme is often inappropriate to deal with different characteristics of users or POIs. Thus, in this paper, we propose PREMERE, an adaptive weighting scheme based on metalearning. Because meta-data is typically required by metalearning but is inherently hard to obtain in POI recommendation, we self-generate the meta-data via self-ensembling. Furthermore, the meta-model architecture is extended to deal with the scarcity of check-ins. Thorough experiments show that replacing a weighting scheme with PREMERE boosts the performance of the state-of-the-art recommender algorithms by 2. 36–26. 9% on three benchmark datasets.

PDF Details

NeurIPS Conference 2021 Conference Paper

Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data

Dongmin Park
Hwanjun Song
Minseok Kim
Jae-Gil Lee

A deep neural network (DNN) has achieved great success in many machine learning tasks by virtue of its high expressive power. However, its prediction can be easily biased to undesirable features, which are not essential for solving the target task and are even imperceptible to a human, thereby resulting in poor generalization. Leveraging plenty of undesirable features in out-of-distribution (OOD) examples has emerged as a potential solution for de-biasing such features, and a recent study shows that softmax-level calibration of OOD examples can successfully remove the contribution of undesirable features to the last fully-connected layer of a classifier. However, its applicability is confined to the classification task, and its impact on a DNN feature extractor is not properly investigated. In this paper, we propose Taufe, a novel regularizer that deactivates many undesirable features using OOD examples in the feature extraction layer and thus removes the dependency on the task-specific softmax layer. To show the task-agnostic nature of Taufe, we rigorously validate its performance on three tasks, classification, regression, and a mix of them, on CIFAR-10, CIFAR-100, ImageNet, CUB200, and CAR datasets. The results demonstrate that Taufe consistently outperforms the state-of-the-art method as well as the baselines without regularization.

PDF Details

ICML Conference 2019 Conference Paper

SELFIE: Refurbishing Unclean Samples for Robust Deep Learning

Hwanjun Song
Minseok Kim
Jae-Gil Lee 0001

Owing to the extremely high expressive power of deep neural networks, their side effect is to totally memorize training data even when the labels are extremely noisy. To overcome overfitting on the noisy labels, we propose a novel robust training method called SELFIE. Our key idea is to selectively refurbish and exploit unclean samples that can be corrected with high precision, thereby gradually increasing the number of available training samples. Taking advantage of this design, SELFIE effectively prevents the risk of noise accumulation from the false correction and fully exploits the training data. To validate the superiority of SELFIE, we conducted extensive experimentation using four real-world or synthetic data sets. The result showed that SELFIE remarkably improved absolute test error compared with two state-of-the-art methods.

Details

JBHI Journal 2015 Journal Article

Simulation-Based Scenario-Specific Channel Modeling for WBAN Cooperative Transmission Schemes

Jun-ichi Naganawa
Karma Wangchuk
Minseok Kim
Takahiro Aoyagi
Jun-ichi Takada

Wireless body area networks (WBANs) are an emerging technology for realizing efficient healthcare and remote medicine for the aging society of the future. In order to improve the reliability of WBAN systems and support its various applications, channel modeling and performance evaluation are important. This paper proposes a simulation-based channel modeling for evaluating the performance of WBAN cooperative transmission schemes. The time series of path losses among seven on-body nodes are generated by the finite-difference time-domain method for seven body motions. The statistical parameters of the path loss for all the motions are also obtained. The generated path loss is then applied to the evaluation of the two-hop decode-and-forward relaying scheme, yielding an improvement in transmit power. From the evaluation of body motion, useful insights are obtained such as which relay links are more robust than others. Finally, the proposed approach is validated through comparison with a measurement-based approach.

Details DOI