Jeongwhan Choi

Yonsei University · Department of Artificial Intelligence

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present t...

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present t...

Owing to the remarkable development of deep learning technology, there have been a series of efforts to build deep learning-based climate models. Whereas most of them utilize recurrent neural networks and/or graph neural networks, we design a novel climate model based on two concepts, the neural ordinary differential equation (NODE) and the advecti...

Graph neural networks (GNNs) are one of the most popular research topics for deep learning. GNN methods typically have been designed on top of the graph signal processing theory. In particular, diffusion equations have been widely used for designing the core processing layer of GNNs and therefore, they are inevitably vulnerable to the oversmoothing...

Forecasting future outcomes from recent time series data is not easy, especially when the future data are different from the past (i.e. time series are under temporal drifts). Existing approaches show limited performances under data drifts, and we identify the main reason: It takes time for a model to collect sufficient training data and adjust its...

Collaborative filtering is one of the most influential recommender system types. Various methods have been proposed for collaborative filtering, ranging from matrix factorization to graph convolutional methods. Being inspired by recent successes of GF-CF and diffusion models, we present a novel concept of blurring-sharpening process model (BSPM). D...

Many U.S. metropolitan cities are notorious for their severe shortage of parking spots. To this end, we present a proactive prediction-driven optimization framework to dynamically adjust parking prices. We use state-of-the-art deep learning technologies such as neural ordinary differential equations (NODEs) to design our future parking occupancy ra...

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present t...

Poster at AAAI 2022, "Graph Neural Controlled Differential Equations for Traffic Forecasting"

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present t...

There were fierce debates on whether the non-linear embedding propagation of GCNs is appropriate to GCN-based recommender systems. It was recently found that the linear embedding propagation shows better accuracy than the non-linear embedding propagation. Since this phenomenon was discovered especially in recommender systems, it is required that we...

Owing to the remarkable development of deep learning technology, there have been a series of efforts to build deep learning-based climate models. Whereas most of them utilize recurrent neural networks and/or graph neural networks, we design a novel climate model based on the two concepts, the neural ordinary differential equation (NODE) and the dif...

Collaborative filtering (CF) is a long-standing problem of recommender systems. Many novel methods have been proposed, ranging from classical matrix factorization to recent graph convolutional network-based approaches. After recent fierce debates, researchers started to focus on linear graph convolutional networks (GCNs) with a layer combination, w...

Collaborative filtering (CF) is a long-standing problem of recommender systems. Many novel methods have been proposed, ranging from classical matrix factorization to recent graph convolutional network-based approaches. After recent fierce debates, researchers started to focus on linear graph convolutional networks (GCNs) with a layer combination, w...

최근 소프트웨어 결함 예측 연구는 교차 프로젝트 간의 결함 예측 뿐만 아니라 교차 버전 프로젝트 간의 결함 예측 또한 이루어지고 있다. 종래의 교차 버전 결함 예측 연구들은 WP(Within-Project)로 가정 한다. 하지만, CV(Cross-Version) 환경에서는 프로젝트 버전 간의 분포 차이 또한 중요하다. 본 연구에서는 다른 버전 간의 분포 차이까지 고려하는 자동화된 베이지안 최적화 프레임워크를 제안한다. 이를 통해 분포 차이에 따라 전이 학습(Transfer Learning) 수행 여부를 자동으로 선택하여 준다. 해당 프레임워크는 버전 간의 분포 차이, 전이 학습과 분류기(Classifier)의 하이퍼파라...

Configuration bugs are one of the main causes of software failure. Software organizations collect and manage bug reports using an issue tracking system. The bug assignor can spend excessive amounts of time identifying whether a bug is a configuration bug or not. Configuration bug prediction can help the bug assignor reduce classification efforts an...

Configuration 버그는 소프트웨어 실패의 주요한 원인들 중 하나이다. 소프트웨어 조직들은 이슈 트래커 시스템을 통해 버그 리포트들을 수집하고 관리한다. 소프트웨어 개발자는 해당 버그가 Configuration 버 그인지 인지하는데 막대한 시간을 소비할 수도 있다. Configuration 버그라는 것을 알 수 있는 접근 방법 을 통해 개발자의 노력을 줄일 수 있다. 이러한 접근 방식을 Configuration 버그 리포트 예측이라고 칭하 며, 해당 문제를 해결하기 위해 텍스트 마이닝 기법을 사용하여 분류 모델을 생성한다. 개발자는 이러한 모델을 사용하여 버그 리포트에 Configuration 또는 Non-con...

In the era of rapid growth in the consumption of news through Internet media, the problems caused by Internet news whose text is not in line with the context of news consumer's predictions through headlines are pervasive because the media is not properly practicing the role of journalism. In order to solve this problem, efforts were made at home an...

Monitoring through Synthesis Aperture Radar (SAR) is responsible for marine safety from floating icebergs. However, there are limits to distinguishing between icebergs and ships in SAR images. Convolutional Neural Network (CNN) is used to distinguish the iceberg from the ship. The goal of this paper is to increase the accuracy of identifying iceber...