We are a research group headed by Prof. Jaekyun Moon in the School of EE at KAIST. We work on distributed and decentralized forms of machine learning, storage and communications, dealing with optimal ways to store, access and process big data in today's densely connected world. Distributed and decentralized ways of data storage and machine learning are essential in the era of IoT, big data and connected AI.


2023.12 W. Choi's paper entitled "Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration" accepted for publication in AAAI Conference on Artificial Intelligence (AAAI)
2023.10 D.-J. Han's paper entitled "Federated Split Learning with Joint Personalization-Generalization for Inference-Stage Optimization in Wireless Edge Networks" accepted for publication in IEEE Transactions on Mobile Computing
2023.09 Three papers accepted to NeurIPS 2023: (Congratulations!)
  • "StableFsDG: Style and Attention Based Learning for Federated Domain Generalization"
  • "Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks"
  • "EvoFed: Leveraging Evolutionary Strategies for Efficient and Privacy-Preserving Federated Learning"
  • 2023.05 D.-J. Han and J. Park's paper entitled "Improving Low-Latency Predictions in Multi-Exit Neural Networks via Block-Dependent Losses" accepted for publication in IEEE Transactions on Neural Networks and Learning Systems
    2023.04 J. Park and D.-J. Han's paper entitled "Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization" accepted to ICML 2023
    2023.03 Y. Park's paper entitled "Distribution Aware Active Learning via Gaussian Mixtures" accepted to ICLR Workshop on Pitfalls of limited data and computation for Trustworthy ML
    2023.01 Two papers accepted to ICLR 2023:
  • "Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation"
  • "Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning"
  • 2022.12 D.-J. Han's paper entitled "SplitGP: Achieving Both Generalization and Personalization in Federated Learning," accepted to IEEE INFOCOM 2023
    2022.08 S. Kim's paper entitled "Deep Neural Network Compression for Image Inpainting," accepted to ECCV Workshop
    2022.06 Two papers accepted to ICML Workshop:
  • "Style Balancing and Test-Time Style Shifting for Domain Generalization"
  • "Locally Supervised Learning with Periodic Global Guidance"
  • 2022.05 J. Sohn's paper entitled "GenLabel: Mixup Relabeling using Generative Models" accepted to ICML 2022
    2022.04 Two papers accepted to CVPR Workshop:
  • "Training Multi-Exit Architectures via Block-Dependent Losses for Anytime Inference"
  • "Active Object Detection with Epistemic Uncertainty and Hierarchical Information Aggregation"
  • 2022.04 D.-J. Han received the Best Ph.D. Dissertation Award from KAIST EE
    2021.10 Y. Park's paper entitled "CAFENet: Class-Agnostic Few-Shot Edge Detection Network" accepted to BMVC 2021
    2021.09 Two papers accepted to NeurIPS 2021:
  • "Few-Round Learning for Federated Learning"
  • "Sageflow: Robust Federated Learning against Both Stragglers and Adversaries"
  • 2021.08 D.-J. Han's paper entitled "FedMes: Speeding Up Federated Learning with Multiple Edge Servers" accepted for publication in IEEE Journal on Selected Areas in Communications
    2021.07 Two papers accepted to ICML Workshop:
  • "Accelerating Federated Learning with Split Learning on Locally Generated Losses"
  • "Handling Both Stragglers and Adversaries for Robust Federated Learning"
  • 2021.06 D.-J. Han's paper entitled "Coded Wireless Distributed Computing with Packet Losses and Retransmissions" accepted for publication in IEEE Transactions on Wireless Communications
    2020.12 D.-J. Han's paper entitled "TiBroco: A Fast and Secure Distributed Learning Framework for Tiered Wireless Edge Networks" accepted to IEEE INFOCOM 2021
    2020.12 M. Choi's paper entitled "Probabilistic Caching and Dynamic Delivery Policies for Categorized Contents and Consecutive User Demands" accepted for publication in IEEE Transactions on Wireless Communications
    2020.11 D.-J. Han's paper entitled "Hierarchical Broadcast Coding: Expediting Distributed Learning at the Wireless Edge" accepted for publication in IEEE Transactions on Wireless Communications
    2020.10 S. Park's paper entitled "Characterization of Inter-Cell Interference in 3D NAND Flash Memory" accepted for publication in IEEE Transactions Circuits and Systems I: Regular Papers
    2020.09 J. Sohn's paper entitled "Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks" accepted to Neural Information Processing Systems (NeurIPS) 2020
    2020.07 J. Sohn's paper entitled "GAN-mixup: Augmenting Across Data Manifolds for Improved Robustness" accepted to ICML Workshop on Uncertainty & Robustness in Deep Learning
    2020.06 S. W. Yoon and D.-Y. Kim's paper entitled "XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning" accepted to International Conference on Machine Learning (ICML) 2020
    2020.03 Dr. Sung Whan Yoon, a Ph.D. alumnus of our group joined UNIST as an Assistant Professor
    2020.03 Dr. Minseok Choi, a Ph.D. alumnus of our group joined Jeju National University as an Assistant Professor
    2020.03 So Yeong Kim and Jinho Kim joined our lab. Welcome!
    2019.07 M. Choi's paper entitled “Dynamic Power Allocation and User Scheduling for Power-Efficient and Delay-Constrained Multiple Access Networks” accepted for publication in IEEE Transactions on Wireless Communications
    2019.06 B. Choi's paper entitled "Secure Clustered Distributed Storage Against Eavesdropping" accepted for publication in IEEE Transactions on Information Theory
    2019.04 S. W. Yoon and J. Seo's paper entitled "TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning" accepted to the 36th International Conference on Machine Learning (ICML) 2019
    2019.04 Four papers accepted in IEEE International Symposium on Information Theory (ISIT) 2019
  • H. Park and J. Moon, "Irregular Product Coded Computation for High-Dimensional Matrix Multiplication"
  • B. Choi, J. Sohn, D.-J. Han and J. Moon, "Scalable Network-Coded PBFT Consensus Algorithm"
  • D.-J. Han, J. Sohn and J. Moon, "Coded Distributed Computing over Packet Erasure Channels"
  • M. Kim, J. Sohn and J. Moon, "Coded Matrix Multiplication on a Group-Based Model"
  • Copyright © Moon Lab., 2017
    School of Electrical Engineering, Korea Advanced Institute of Science and Technology
    291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea