Author name cluster

Yongjae Lee

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.

4 papers

1 author row

AAAI Conference 2025 Conference Paper

Geodesic Flow Kernels for Semi-Supervised Learning on Mixed-Variable Tabular Dataset

Yoontae Hwang
Yongjae Lee

Tabular data poses unique challenges due to its heterogeneous nature, combining both continuous and categorical variables. Existing approaches often struggle to effectively capture the underlying structure and relationships within such data. We propose GFTab (Geodesic Flow Kernels for Semi-Supervised Learning on Mixed-Variable Tabular Dataset), a semi-supervised framework specifically designed for tabular datasets. GFTab incorporates three key innovations: 1) Variable-specific corruption methods tailored to the distinct properties of continuous and categorical variables, 2) A Geodesic flow kernel based similarity measure to capture geometric changes between corrupted inputs, and 3) Tree-based embedding to leverage hierarchical relationships from available labeled data. To rigorously evaluate GFTab, we curate a comprehensive set of 21 tabular datasets spanning various domains, sizes, and variable compositions. Our experimental results show that GFTab outperforms existing ML/DL models across many of these datasets, particularly in settings with limited labeled data.

PDF Details DOI

EAAI Journal 2025 Journal Article

Machine learning for disease-specific prediction of high-cost patients

Inwoo Tae
Hyeongwoo Kong
Junghye Lee
Yongjae Lee

High-cost patients incur disproportionately high medical expenses, and identifying them proactively is crucial for effective healthcare management. While previous research has focused on identifying high-cost patients based on overall expenditure, there has been a lack of studies analyzing them in the context of specific diseases. This study addressed this gap by leveraging data from the National Health Insurance Service (NHIS) of South Korea, spanning 2015 to 2019, to develop predictive models for identifying these patients. We trained models using data from 880, 000 individuals to predict high-cost patients in 2019 using resource-efficient machine learning algorithms such as Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Neural Networks (NN) that minimize computational overhead, with undersampling techniques applied to handle data imbalance. We focused on the six major disease categories that account for the highest medical expenditures in South Korea: diseases of the musculoskeletal system (DMS), circulatory system (DCS), eye and ear (DEA-DEM), digestive system (DDS), genitourinary system (DGS), and respiratory system (DRS). We discovered that disease-specific analyses revealed important predictive factors that were not apparent in aggregate analyses. For example, hemoglobin levels emerged as crucial predictors for DCS, while body mass index (BMI) proved essential for DMS prediction. These findings enhance our understanding of the factors contributing to high medical costs and provide a foundational framework for healthcare providers and policymakers to develop more targeted and effective health management strategies.

Details DOI

NeurIPS Conference 2024 Conference Paper

LP-3DGS: Learning to Prune 3D Gaussian Splatting

Zhaoliang Zhang
Tianchen Song
Yongjae Lee
Li Yang
Cheng Peng
Rama Chellappa
Deliang Fan

Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a point-based scene representation, 3DGS potentially generates a large number of Gaussians to fit the scene, leading to high memory usage. Improvements that have been proposed require either an empirical pre-set pruning ratio or importance score threshold to prune the point cloud. Such hyperparameters require multiple rounds of training to optimize and achieve the maximum pruning ratio while maintaining the rendering quality for each scene. In this work, we propose learning-to-prune 3DGS (LP-3DGS), where a trainable binary mask is applied to the importance score to automatically find a favorable pruning ratio. Instead of using the traditional straight-through estimator (STE) method to approximate the binary mask gradient, we redesign the masking function to leverage the Gumbel-Sigmoid method, making it differentiable and compatible with the existing training process of 3DGS. Extensive experiments have shown that LP-3DGS consistently achieves a good balance between efficiency and high quality.

PDF Details DOI

EAAI Journal 2024 Journal Article

Multi-attention recommender system for non-fungible tokens

Yejin Kim
Seonmi Kim
Youngbin Lee
Joohwan Hong
Yongjae Lee

Recommender systems have become essential tools for enhancing user experiences across various domains. While extensive research has been conducted on recommender systems for movies, music, and e-commerce, the rapidly growing and economically significant Non-Fungible Token (NFT) market remains underexplored. Recommender systems have the potential to significantly enhance user engagement, increase the time users spend on platforms, and deepen user involvement. Consequently, effective implementation of such systems could serve as a catalyst for invigorating the NFT market. However, the unique characteristics of the NFT market, such as the high sparsity of user–item interactions, anonymity of blockchain, and dual nature, present challenges not encountered in traditional recommender systems, highlighting the importance of developing tailored solutions to cater to its specific needs and unlock its full potential. In this paper, we examine the distinctive characteristics of NFTs and propose the first recommender system specifically designed to address NFT market challenges. In specific, we develop a Multi-Attention Recommender System for NFTs (NFT-MARS) with three key characteristics: (1) graph attention to handle sparse user–item interactions, (2) multi-modal attention to incorporate feature preference of users, and (3) multi-task learning to consider the dual nature of NFTs as both artwork and financial assets. We demonstrate the effectiveness of NFT-MARS compared to various baseline models using the actual transaction data of NFTs collected directly from the blockchain for four of the most popular NFT collections.

Details DOI