Publications

2024

1. ICML

   Pursuing Overall Welfare in Federated Learning through Sequential Decision Making

   Seok-Ju Hahn, Gi-Soo Kim, and Junghye Lee

   2024.

   (acceptance rate = 27.5%)

   Bib HTML PDF Video Code Poster

   @article{hahn24aaggff,
     title = {Pursuing Overall Welfare in Federated Learning through Sequential Decision Making},
     author = {Hahn, Seok-Ju and Kim, Gi-Soo and Lee, Junghye},
     booktitle = {Proceedings of the 41st International Conference on Machine Learning},
     pages = {17246--17278},
     year = {2024},
     publisher = {Proceedings of Machine Learning Resaerch, PMLR},
   }
2. KDD

   CAFO: Feature-Centric Explanation on Time Series Classification

   Jaeho Kim*, Seok-Ju Hahn*, Yoontae Hwang*, Junghye Lee, and Seulki Lee

   arXiv preprint arXiv:2406.01833, 2024.

   [NOTE: To appear at KDD 2024]

   (acceptance rate = 20.0%)

   Bib HTML PDF Video Code Poster

   @article{kim24cafo,
     title = {CAFO: Feature-Centric Explanation on Time Series Classification},
     author = {Kim, Jaeho and Hahn, Seok-Ju and Hwang, Yoontae and Lee, Junghye and Lee, Seulki},
     journal = {arXiv preprint arXiv:2406.01833},
     year = {2024},
     publisher = {Association for Computing Machinery, New York, NY, United States},
   }

2022

1. KDD

   Connecting Low-Loss Subspace for Personalized Federated Learning

   Seok-Ju Hahn, Minwoo Jeong, and Junghye Lee

   In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , 2022.

   [NOTE: Work done at Kakao Enterprise during AI Research Internship]

   (acceptance rate = 14.9%)

   Bib HTML PDF Video Code Poster

   @inproceedings{hahn22superfed,
     title = {Connecting Low-Loss Subspace for Personalized Federated Learning},
     author = {Hahn, Seok-Ju and Jeong, Minwoo and Lee, Junghye},
     booktitle = {Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
     pages = {505--515},
     year = {2022},
     publisher = {Association for Computing Machinery, New York, NY, United States},
   }

2. EBIOM

   Prediction of Type 2 Diabetes using Genome-Wide Polygenic Risk Score and Metabolic Profiles: A Machine Learning Analysis of Population-based 10-Year Prospective Cohort Study

   Seok-Ju Hahn*, Suhyeon Kim*, Young Sik Choi, Junghye Lee, and Jihun Kang

   EBioMedicine, 2022.

   (impact factor = 11.1)

   Bib HTML PDF Code

   @article{hahn22t2d,
     title = {Prediction of Type 2 Diabetes using Genome-Wide Polygenic Risk Score and Metabolic Profiles: A Machine Learning Analysis of Population-based 10-Year Prospective Cohort Study},
     author = {Hahn, Seok-Ju and Kim, Suhyeon and Choi, Young Sik and Lee, Junghye and Kang, Jihun},
     journal = {EBioMedicine},
     volume = {86},
     year = {2022},
     publisher = {Elsevier},
   }