Dongha Lee

Dongha Lee

Assistant Professor at Yonsei University

Biography

I am an Assistant Professor in the Department of Artificial Intelligence at Yonsei University. I received my Ph.D. in Computer Science from Pohang University of Science and Technology, where I was advised by Prof. Hwanjo Yu. After completing my Ph.D., I worked as a postdoctoral research fellow at the University of Illinois at Urbana-Champaign with my advisor, Prof. Jiawei Han.

My research interest lies in applied machine learning, which aims to develop practical ML solutions for real-world applications. I have covered a wide range of data types (e.g., matrix/tensor, text, graph, time series), tasks (e.g., classification, outcome prediction, anomaly detection, retrieval, data generation), and domains (e.g., healthcare, manufacturing, recommender systems).

Research Interest

  • Knowledge discovery from massive real-world data
  • Text mining and NLP applications
  • Deep learning approaches to real-world applications

Publications

2023

  • Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding
    Susik Yoon, Dongha Lee, Yunyi Zhang, Jiawei Han
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2023
    [paper] [code]

  • SCStory: Self-supervised and Continual Online Story Discovery
    Susik Yoon, Yu Meng, Dongha Lee, Jiawei Han
    The ACM Web Conference (WWW), 2023
    [paper] [code]

  • Distillation from Heterogeneous Models for Top-K Recommendation
    Seongku Kang, Wonbin Kweon, Dongha Lee, Jianxun Lian, Xing Xie, Hwanjo Yu
    The ACM Web Conference (WWW), 2023
    [paper] [code]

  • Learning Topology-Specific Experts for Molecular Property Prediction
    Su Kim, Dongha Lee, Seongku Kang, Seonghyeon Lee, Hwanjo Yu
    AAAI Conference on Artificial Intelligence (AAAI), 2023
    [paper] [code]

2022

  • Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation
    Dongha Lee, Jiaming Shen, Seonghyeon Lee, Susik Yoon, Hwanjo Yu, Jiawei Han
    Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2022
    [paper] [code]

  • Measurement of Image Conformity for Viewpoint-robust One-class Classification
    Hyunjun Ju, Dongha Lee, Seongku Kang, Hwanjo Yu
    Information Sciences, 2022 (SCI)
    [paper] [code]

  • Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning
    Seonghyeon Lee, Dongha Lee, Seongbo Jang, Hwanjo Yu
    Annual Conference of the Association for Computational Linguistics (ACL), 2022
    [paper] [code]

  • TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
    Dongha Lee, Jiaming Shen, Seongku Kang, Susik Yoon, Jiawei Han, Hwanjo Yu
    The ACM Web Conference (WWW), 2022
    [paper] [code]

  • Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering
    Seongku Kang, Dongha Lee, Wonbin Kweon, Junyoung Hwang, Hwanjo Yu
    The ACM Web Conference (WWW), 2022
    [paper] [code]

  • Personalized Knowledge Distillation for Recommender System
    Seongku Kang, Dongha Lee, Wonbin Kweon, Hwanjo Yu
    Knowledge-Based Systems, 2022 (SCI)
    [paper] [code]

2021

  • Out-of-Category Document Identification Using Target-Category Names as Weak Supervision
    Dongha Lee, Dongmin Hyun, Jiawei Han, Hwanjo Yu
    IEEE International Conference on Data Mining (ICDM), 2021
    [paper] [code]

  • Learnable Structural Semantic Readout for Graph Classification
    Dongha Lee, Su Kim, Seonghyeon Lee, Chanyoung Park, Hwanjo Yu
    IEEE International Conference on Data Mining (ICDM), 2021
    [paper] [code]

  • Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping
    Dongha Lee, Sehun Yu, Hyunjun Ju, Hwanjo Yu
    IEEE International Conference on Computer Vision (ICCV), 2021
    [paper] [code]

  • Out-of-manifold Regularization in Contextual Embedding Space for Text Classification
    Seonghyeon Lee, Dongha Lee, Hwanjo Yu
    Annual Conference of the Association for Computational Linguistics (ACL), 2021
    [paper] [code]

  • Bootstrapping User and Item Representations for One-Class Collaborative Filtering
    Dongha Lee, Seongku Kang, Hyunjun Ju, Chanyoung Park, Hwanjo Yu
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2021
    [paper] [code]

  • Learnable Dynamic Temporal Pooling for Time Series Classification
    Dongha Lee, Seonghyeon Lee, Hwanjo Yu
    AAAI Conference on Artificial Intelligence (AAAI), 2021
    [paper] [code]

2020

  • Multi-class Data Description for Out-of-distribution Detection
    Dongha Lee, Sehun Yu, Hwanjo Yu
    ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD), 2020
    [paper] [code]

  • Generating Sequential Electronic Health Records using Dual Adversarial Autoencoder
    Dongha Lee, Hwanjo Yu, Xiaoqian Jiang, Deevakar Rogith, Meghana Gudala, Mubeen Tejani, Qiuchen Zhang, Li Xiong
    Journal of the American Medical Informatics Association (JAMIA), 2020 (SCI)
    [paper] [code] [webpage]

  • Harmonized Representation Learning on Dynamic EHR Graphs
    Dongha Lee, Xiaoqian Jiang, Hwanjo Yu
    Journal of Biomedical Informatics, 2020 (SCI)
    [paper] [code]

  • Convolutional Neural Networks with Compression Complexity Pooling for Out-of-Distribution Image Detection
    Sehun Yu, Dongha Lee, Hwanjo Yu
    International Joint Conference on Artificial Intelligence (IJCAI), 2020
    [paper] [code]

  • PUMAD: PU Metric Learning for Anomaly Detection
    Hyunjun Ju, Dongha Lee, Junyoung Hwang, Junghyun Namkung, Hwanjo Yu
    Information Sciences, 2020 (SCI)
    [paper]

  • Scalable Disk-based Topic Modeling for Memory Limited Devices
    Byungju Kim, Dongha Lee, Jinoh Oh, Hwanjo Yu
    Information Sciences, 2020 (SCI)
    [paper]

  • OCAM: Out-of-core Coordinate Descent Algorithm for Matrix Completion
    Dongha Lee, Jinoh Oh, Hwanjo Yu
    Information Sciences, 2020 (SCI)
    [paper] [code] [webpage]

  • Large-Scale Matrix and Tensor Completion based on Out-of-Core Approaches
    Dongha Lee
    Ph.D. Dissertation, 2020
    [paper]

2019

  • Semi-Supervised Learning for Cross-Domain Recommendation to Cold-Start Users
    Seongku Kang, Junyoung Hwang, Dongha Lee, Hwanjo Yu
    ACM International Conference on Information and Knowledge Management (CIKM), 2019
    [paper]

  • Action Space Learning for Heterogeneous User Behavior Prediction
    Dongha Lee, Chanyoung Park, Hyunjun Ju, Junyoung Hwang, Hwanjo Yu
    International Joint Conference on Artificial Intelligence (IJCAI), 2019
    [paper] [code]

2018

  • Fast Tucker Factorization for Large-scale Tensor Completion
    Dongha Lee, Jaehyung Lee, Hwanjo Yu
    IEEE International Conference on Data Mining (ICDM), 2018
    [paper] [code] [webpage]

  • Disk-based Matrix Completion for Memory Limited Devices
    Dongha Lee, Jinoh Oh, Christos Faloutsos, Byungju Kim, Hwanjo Yu
    ACM International Conference on Information and Knowledge Management (CIKM), 2018
    [paper] [webpage]

  • DualSentiNet: Dual Prediction of Word and Document Sentiments Using Shared Word Embedding
    Dongha Lee, Hyunjun Ju, Jung-Mi Park, Kye-Yoon Kim, Hwanjo Yu
    ACM International Conference on Ubiquitous Information Management and Communication (IMCOM), 2018
    [paper]

2017

  • Compressing Model for Matrix Factorization with Quantization Using k-means Clustering
    Junsu Cho, Dongha Lee, Hwanjo Yu
    Korean Database Conference (KDBC), 2017

2016

  • GeoVideoIndex: Indexing for Georeferenced Videos
    Dongha Lee, Jinoh Oh, Woong-Kee Loh, Hwanjo Yu
    Information Sciences, 2016 (SCI)
    [paper]

Work Experience

  • University of Illinois at Urbana-Champaign (UIUC), United States
    Postdoctoral Research Fellow, 2021.07 -
    Department of Computer Science
    Advisor: Prof. Jiawei Han
  • Pohang University of Science and Technology (POSTECH), South Korea
    Postdoctoral Researcher, 2020.03 - 2021.06
    Department of Computer Science and Engineering
    Advisor: Prof. Hwanjo Yu
  • University of Texas Health Science Center at Houston (UT Health), United States
    Visiting Scholar, 2018.09 - 2019.02
    School of Biomedical Informatics
    Advisor: Prof. Xiaoqian Jiang

Education

  • Pohang University of Science and Technology (POSTECH), South Korea
    Ph.D. in Computer Science and Engineering, 2015.03 - 2020.02
    Large-scale Matrix and Tensor Completion based on Out-of-core Approaches
    Advisor: Prof. Hwanjo Yu
  • Technical University of Berlin (TU Berlin), Germany
    B.S. in Computer Science, 2013.10 - 2014.02
    Exchange Student
  • Pohang University of Science and Technology (POSTECH), South Korea
    B.S. in Computer Science and Enginnering, 2011.03 - 2015.02
    Summa Cum Laude (Ranked 1st in the Department)

Honors & Awards

  • ACM CIKM Student Travel Award (2018)
  • Naver Ph.D. Fellowship (2018)
  • POSTECH CSE Graduate Fellowship (2015)
  • Kwanjeong Educational Fellowship (2013 - 2016)