Publications

 Journals & Top Conferences (* equal contribution / corresponding author)


[22] Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning

         Do-Yeon Kim, Dong-Jun Han*, Jun Seo, and Jaekyun Moon

         International Conference on Machine Learning (ICML), July 2024.


[21] Cooperative Federated Learning over Ground-to-Satellite Integrated Networks: Joint Local Computation and Data Offloading [paper]

         Dong-Jun Han, Seyyedali Hosseinalipour, David J. Love, Mung Chiang, and Christopher G. Brinton

         IEEE Journal on Selected Areas in Communications (JSAC) - Special Issue on Space Communications New Frontiers: From Near Earth to Deep Space, May 2024.


[20] Federated Split Learning with Joint Personalization-Generalization for Inference-Stage Optimization in Wireless Edge Networks [paper]

         Dong-Jun Han, Do-Yeon Kim, Minseok Choi, David Nickel, Jaekyun Moon, Mung Chiang, and Christopher G. Brinton

         IEEE Transactions on Mobile Computing (TMC), June 2024.


[19] Consistency-Guided Temperature Scaling using Style and Content Information for Out-of-Domain Calibration [paper]

         Wonjeong Choi, Jungwuk Park, Dong-Jun Han*, Younghyun Park, and Jaekyun Moon

         AAAI Conference on Artificial Intelligence (AAAI), Feb. 2024.


[18] StableFDG: Style and Attention Based Learning for Federated Domain Generalization [paper]

         Jungwuk Park*, Dong-Jun Han*, Jinho Kim, Shiqiang Wang, Christopher G. Brinton, and Jaekyun Moon

         Neural Information Processing Systems (NeurIPS), Dec. 2023.


[17] NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks [paper]

         Seokil Ham, Jungwuk Park, Dong-Jun Han*, and Jaekyun Moon

         Neural Information Processing Systems (NeurIPS), Dec. 2023.


[16] Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization [paper]

          Jungwuk Park*, Dong-Jun Han*, Soyeong Kim, and Jaekyun Moon

          International Conference on Machine Learning (ICML), July 2023.


[15] SplitGP: Achieving Both Generalization and Personalization in Federated Learning [paper]

          Dong-Jun Han, Do-Yeon Kim, Minseok Choi, Christopher G. Brinton, and Jaekyun Moon

          IEEE International Conference on Computer Communications (INFOCOM), May 2023 (Acceptance rate: 19.2%).


[14] Improving Low-Latency Predictions in Multi-Exit Neural Networks via Block-Dependent Losses [paper]

         Dong-Jun Han*, Jungwuk Park*, Seokil Ham, Namjin Lee, and Jaekyun Moon

         IEEE Transactions on Neural Networks and Learning Systems (TNNLS), accepted, 2023.


[13] Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning [paper]

          Do-Yeon Kim, Dong-Jun Han*, Jun Seo, and Jaekyun Moon

          International Conference on Learning Representations (ICLR), May 2023 (Spotlight: notable-top-25%).


[12] Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation [paper]

          Younghyun Park, Soyeong Kim, Wonjeong Choi, Dong-Jun Han*, and Jaekyun Moon

          International Conference on Learning Representations (ICLR), May 2023.


[11] FedMes: Speeding Up Federated Learning with Multiple Edge Servers [paper]

         Dong-Jun Han, Minseok Choi, Jungwuk Park, and Jaekyun Moon

         IEEE Journal on Selected Areas in Communications (JSAC) - Special Issue on Distributed Learning over Wireless Edge Networks, Dec. 2021.


[10] Coded Wireless Distributed Computing with Packet Losses and Retransmissions [paper] 

         Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon

         IEEE Transactions on Wireless Communications (TWC), Dec. 2021.


[9] Few-Round Learning for Federated Learning [paper]

       Younghyun Park*, Dong-Jun Han*, Do-Yeon Kim, Jun Seo, and Jaekyun Moon 

       Neural Information Processing Systems (NeurIPS), Dec. 2021.


[8] Sageflow: Robust Federated Learning against Both Stragglers and Adversaries [paper]

       Jungwuk Park*, Dong-Jun Han*, Minseok Choi, and Jaekyun Moon 

       Neural Information Processing Systems (NeurIPS), Dec. 2021.


[7] TiBroco: A Fast and Secure Distributed Learning Framework for Tiered Wireless Edge Networks [paper]

       Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon

       IEEE International Conference on Computer Communications (INFOCOM), May 2021 (Acceptance rate: 19.9%).


[6] Hierarchical Broadcast Coding: Expediting Distributed Learning at the Wireless Edge [paper]

       Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon

       IEEE Transactions on Wireless Communications (TWC), Apr. 2021 (Qualcomm-KAIST Innovation Award).


[5] Probabilistic Caching and Dynamic Delivery Policies for Categorized Contents and Consecutive User Demands [paper]

       Minseok Choi, Andreas F. Molisch, Dong-Jun Han, Dongjae Kim, Joongheon Kim, and Jaekyun Moon

       IEEE Transactions on Wireless Communications (TWC), Apr. 2021.


[4] Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks [paper]

       Jy-yong Sohn, Dong-Jun Han, Beongjun Choi, and Jaekyun Moon

       Neural Information Processing Systems (NeurIPS), Dec. 2020.


[3] Bi-Directional Cooperative NOMA Without Full CSIT [paper]

       Minseok Choi, Dong-Jun Han, and Jaekyun Moon

       IEEE Transactions on Wireless Communications (TWC), Nov. 2018.


[2] Combined Window-Filter Waveform Design With Transmitter-Side Channel State Information [paper]

       Dong-Jun Han, Jaekyun Moon, Jy-yong Sohn, Sunyoung Jo, and Jang Hun Kim

       IEEE Transactions on Vehicular Technology (TVT), Sep. 2018.


[1] Combined Subband-Subcarrier Spectral Shaping in Multi-Carrier Modulation under the Excess Frame Length Constraint [paper]

       Dong-Jun Han, Jaekyun Moon, Dongjae Kim, Sae-Young Chung, and Yong H. Lee

       IEEE Journal on Selected Areas in Communications (JSAC) - Special Issue on Deployment Issues and Performance Challenges for 5G, June 2017. 



Conferences & Workshops


[14] Cooperative Federated Learning over Hybrid Terrestrial and Non-Terrestrial Networks

         Dong-Jun Han, Seyyedali Hosseinalipour, David J. Love, Mung Chiang, and Christopher G. Brinton

         IEEE International Conference on Communications (ICC), June 2024.


[13] Submodel Partitioning in Hierarchical Federated Learning: Algorithm Design and Convergence Analysis

         Wenzhi Fang, Dong-Jun Han, and Christopher G. Brinton

         IEEE International Conference on Communications (ICC), June 2024.


[12] FedMFS: Federated Multimodal Fusion Learning with Selective Modality Communication

         Liangqi Yuan, Dong-Jun Han, Vishnu Pandi Chellapandi, Stanislaw H Żak, and Christopher G. Brinton

         IEEE International Conference on Communications (ICC), June 2024.


[11] Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation

         Yun-Wei Chu, Dong-Jun Han, and Christopher G. Brinton

         International Workshop on Federated Foundation Models for the Web 2024 (FL@FM-TheWebConf'24), May 2024.


[10] Distribution Aware Active Learning via Gaussian Mixtures [paper]

         Younghyun Park, Dong-Jun Han, Jungwuk Park, Wonjeong Choi, Humaira Kousar, and Jaekyun Moon

         ICLR Workshop on Pitfalls of Limited Data and Computation for Trustworthy ML (ICLR Workshop), May 2023.


[9] Style Balancing and Test-Time Style Shifting for Domain Generalization

      Jungwuk Park*, Dong-Jun Han*, Soyeong Kim, and Jaekyun Moon

      ICML Workshop on Principles of Distribution Shift (ICML Workshop), July 2022.


[8] Training Multi-Exit Architectures via Block-Dependent Losses for Anytime Inference [paper]

       Dong-Jun Han*, Jungwuk Park*, Seokil Ham, Namjin Lee ,and Jaekyun Moon

       CVPR Workshop on Dynamic Neural Networks Meet Computer Vision (CVPR Workshop), June 2022 (Oral).


[7] Active Object Detection with Epistemic Uncertainty and Hierarchical Information Aggregation [paper]

       Younghyun Park, Soyeong Kim, Wonjeong Choi, Dong-Jun Han, and Jaekyun Moon

       CVPR Workshop on Efficient Deep Neural Network for Computer Vision (CVPR Workshop), June 2022.


[6] Accelerating Federated Learning with Split Learning on Locally Generated Losses [paper]

       Dong-Jun Han, Hasnain Irshad Bhatti, Jungmoon Lee, and Jaekyun Moon

       ICML Workshop on Federated Learning for User Privacy and Data Confidentiality (ICML Workshop), July 2021.


[5] Handling Both Stragglers and Adversaries for Robust Federated Learning [paper]

       Jungwuk Park*, Dong-Jun Han*, Minseok Choi, and Jaekyun Moon 

       ICML Workshop on Federated Learning for User Privacy and Data Confidentiality (ICML Workshop), July 2021. 


[4] Cache Allocations for Consecutive Requests of Categorized Contents: Service Provider’s Perspective [paper] 

       Minseok Choi, Andreas Molisch, Dong-Jun Han, Joongheon Kim, and Jaekyun Moon

       IEEE Wireless Communications and Networking Conference (WCNC), Apr. 2020. 


[3] Coded Distributed Computing over Packet Erasure Channels [paper]

       Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon

       IEEE International Symposium on Information Theory (ISIT), July 2019.


[2] Scalable Network-Coded PBFT Consensus Algorithm [paper]

       Beongjun Choi, Jy-yong Sohn, Dong-Jun Han, and Jaekyun Moon

       IEEE International Symposium on Information Theory (ISIT), July 2019.


[1] Probabilistic Caching Policy for Categorized Contents and Consecutive User Demands [paper]

       Minseok Choi, Dongjae Kim, Dong-Jun Han, Joongheon Kim, and Jaekyun Moon

       IEEE International Conference on Communications (ICC), May 2019.



Preprints