4.3k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Seoul National UniversityKR138 papers
- The University of TokyoJP133 papers
- Centre National de la Recherche ScientifiqueFR113 papers
- Pusan National UniversityKR110 papers
- Massachusetts Institute of TechnologyUS105 papers
- Korea Astronomy and Space Science InstituteKR104 papers
- California Institute of TechnologyUS99 papers
- Université Libre de BruxellesBE99 papers
- University of ChicagoUS99 papers
- National Astronomical Observatory of JapanJP97 papers
- Lomonosov Moscow State UniversityRU96 papers
- Universität HamburgDE94 papers
37 papers · 1 filter
Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data
Kiwan Kwon, Kangmin Kim, Hojin Lee +5
Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and research, yet conventional tabular metrics often overlook temporal structure. Existi…
EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning
Ahin Lee, Sehyun Yun, Taesik Gong
Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation. Existing parameter-efficient fine-tuning (PE…
FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
YongKyung Oh, Dong-Young Lim, Sungil Kim
Modeling continuous-time dynamics from sparse and irregularly-sampled time series remains a fundamental challenge. Neural controlled differential equations provide a principled fra…
From Patterns to Predictions: A Shapelet-Based Framework for Directional Forecasting in Noisy Financial Markets
Juwon Kim, Hyunwook Lee, Hyotaek Jeon +2
Directional forecasting in financial markets requires both accuracy and interpretability. Before the advent of deep learning, interpretable approaches based on human-defined patter…
Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equations
YongKyung Oh, Seungsu Kam, Dong-Young Lim +1
Astronomical time series from large-scale surveys like LSST are often irregularly sampled and incomplete, posing challenges for classification and anomaly detection. We introduce a…
TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
YongKyung Oh, Dong-Young Lim, Sungil Kim +1
Handling missing data in time series classification remains a significant challenge in various domains. Traditional methods often rely on imputation, which may introduce bias or fa…
ST-MTM: Masked Time Series Modeling with Seasonal-Trend Decomposition for Time Series Forecasting
Hyunwoo Seo, Chiehyeon Lim
Forecasting complex time series is an important yet challenging problem that involves various industrial applications. Recently, masked time-series modeling has been proposed to ef…
Conditional Temporal Neural Processes with Covariance Loss
Boseon Yoo, Jiwoo Lee, Janghoon Ju +3
We introduce a novel loss function, Covariance Loss, which is conceptually equivalent to conditional neural processes and has a form of regularization so that is applicable to many…
Machine Learning Optimal Ordering in Global Routing Problems in Semiconductors
Heejin Choi, Minji Lee, Chang Hyeong Lee +2
In this work, we propose a new method for ordering nets during the process of layer assignment in global routing problems. The global routing problems that we focus on in this work…
SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization
Kwangryeol Park, Seulki Lee
We propose SMMF (Square-Matricized Momentum Factorization), a memory-efficient optimizer that reduces the memory requirement of the widely used adaptive learning rate optimizers, s…
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…
CAFO: Feature-Centric Explanation on Time Series Classification
Jaeho Kim, Seok-Ju Hahn, Yoontae Hwang +2
In multivariate time series (MTS) classification, finding the important features (e.g., sensors) for model performance is crucial yet challenging due to the complex, high-dimension…
DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis
YongKyung Oh, Dong-Young Lim, Sungil Kim
Real-world time series analysis faces significant challenges when dealing with irregular and incomplete data. While Neural Differential Equation (NDE) based methods have shown prom…
Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Xinyue Ma, Suyeon Jeong, Minjia Zhang +3
Continual learning (CL) trains NN models incrementally from a continuous stream of tasks. To remember previously learned knowledge, prior studies store old samples over a memory hi…
Exploration in Deep Reinforcement Learning: A Survey
Pawel Ladosz, Lilian Weng, Minwoo Kim +1
This paper reviews exploration techniques in deep reinforcement learning. Exploration techniques are of primary importance when solving sparse reward problems. In sparse reward pro…
Testing using Privileged Information by Adapting Features with Statistical Dependence
Kwang In Kim, James Tompkin
Given an imperfect predictor, we exploit additional features at test time to improve the predictions made, without retraining and without knowledge of the prediction function. This…
Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning
Soobee Lee, Minindu Weerakoon, Jonghyun Choi +3
Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks.…
Connecting Low-Loss Subspace for Personalized Federated Learning
Seok-Ju Hahn, Minwoo Jeong, Junghye Lee
Due to the curse of statistical heterogeneity across clients, adopting a personalized federated learning method has become an essential choice for the successful deployment of fede…
Recent Deep Semi-supervised Learning Approaches and Related Works
Gyeongho Kim
This work proposes an overview of the recent semi-supervised learning approaches and related works. Despite the remarkable success of neural networks in various applications, there…
An Empirical Experiment on Deep Learning Models for Predicting Traffic Data
Hyunwook Lee, Cheonbok Park, Seungmin Jin +3
To tackle ever-increasing city traffic congestion problems, researchers have proposed deep learning models to aid decision-makers in the traffic control domain. Although the propos…
Online anomaly detection using statistical leverage for streaming business process events
Jonghyeon Ko, Marco Comuzzi
While several techniques for detecting trace-level anomalies in event logs in offline settings have appeared recently in the literature, such techniques are currently lacking for o…
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards
Kyungjae Lee, Hongjun Yang, Sungbin Lim +1
In this paper, we consider stochastic multi-armed bandits (MABs) with heavy-tailed rewards, whose -th moment is bounded by a constant for . First, we propose a…
Neural Bootstrapper
Minsuk Shin, Hyungjoo Cho, Hyun-seok Min +1
Bootstrapping has been a primary tool for ensemble and uncertainty quantification in machine learning and statistics. However, due to its nature of multiple training and resampling…
An empirical investigation of different classifiers, encoding and ensemble schemes for next event prediction using business process event logs
Bayu Adhi Tama, Marco Comuzzi, Jonghyeon Ko
There is a growing need for empirical benchmarks that support researchers and practitioners in selecting the best machine learning technique for given prediction tasks. In this pap…