Research

Deep Learning & Machine Learning

How can we learn from massive amount of data? We work on designing models, algorithms, and systems for deep learning and machine learning. We focus on the following researches.

Models, Algorithms and Systems:

  • Autonomous machine learning (AutoML): we develop methods to design an AI that learns how to learn automatically.
  • Lightweight machine learning: we aim to build a fast and energy-efficient model.
  • Transferable machine learning: we aim to build a high quality model even when labeled instances are scarce.
  • Anomaly detection, prediction, and one-class classification: we develop models and algorithms for detecting and predicting anomalies and extreme events with applications including machine failure detection and prediction.
  • Object detection and classification using sensors: we develop methods to detect objects and humans using data from various sensors.
  • Question answering: We develop question answering methods using big data and deep neural networks.

Publication

  • Jongjin Kim, Jaeri Lee, Jeongin Yun, and U Kang, "Dependency-Aware Action Planning for Smart Home", PLOS ONE (PLOS ONE), 2024
  • Junghun Kim, Ka Hyun Park, Hoyoung Yoon, and U Kang, "Domain-Aware Data Selection for Speech Classification via Meta-Reweighting", Interspeech, 2024, Kos Island. [HOMEPAGE]
  • Jihyeong Jeon, Jiwon Park, Chanhee Park, and U Kang, "FreQuant: A Reinforcement-Learning based Adaptive Portfolio Optimization with Multi-frequency Decomposition", ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2024, Barcelona, Spain.
  • Junghun Kim, Ka Hyun Park, and U Kang, "Fast and Accurate Domain Adaptation for Irregular Tensor Decomposition", ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2024, Barcelona, Spain. [HOMEPAGE]
  • Junghun Kim, Ka Hyun Park, and U Kang, "Accurate Semi-supervised Automatic Speech Recognition via Multi-hypotheses-based Curriculum Learning", Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2024, Taipei, Taiwan.
  • Sooyeon Shim, Junghun Kim, Ka Hyun Park, and U Kang, "Accurate graph classification via two-staged contrastive curriculum learning", PLOS ONE (PLOS ONE), 2024
  • Seungcheol Park, Hojun Choi, and U Kang, "Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models", International Conference on Learning Representations (ICLR), 2024, Vienna, Austria. [HOMEPAGE]
  • Hyojin Jeon, Seungcheol Park, Jin-gee Kim, and U Kang, "PET: Parameter-efficient Knowledge Distillation on Transformer", PLOS ONE (PLOS ONE), 2023 [PDF] [BIBTEX] [HOMEPAGE]
  • Ikhyun Cho and U Kang, "Pea-KD: Parameter-efficient and accurate knowledge distillation on BERT", PLOS ONE (PLOS ONE), 2022 [PDF] [BIBTEX] [HOMEPAGE]
  • Huiwen Xu and U Kang, "Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance", ICCV, 2023, Paris, France. [HOMEPAGE]
  • Jun-gi Jang and U Kang, "Accurate Open-set Recognition for MemoryWorkload", ACM Transactions on Knowledge Discovery from Data (TKDD), 2023 [PDF] [BIBTEX]
  • Yejun Soun, Jihyeong Jeon, and U Kang, "Accurate Stock Movement Prediction with Self-supervised Learning from Sparse Noisy Tweets", IEEE International Conference on Big Data (BigData), 2022, Osaka, Japan. [PDF] [BIBTEX] [HOMEPAGE]
  • Sooyeon Shim, Doyeon Kim, Jun-gi Jang, and U Kang, "Fast and Accurate Interpretation of Workload Classification Model", PLOS ONE (PLOS ONE), 2023 [PDF] [BIBTEX] [HOMEPAGE]
  • Jun-gi Jang and U Kang, "Falcon: Lightweight and Accurate Convolution Based on Depthwise Separable Convolution", Knowledge and Information Systems (KAIS), 2023 [PDF] [BIBTEX] [HOMEPAGE]
  • Jaemin Yoo, Hyunsik Jeon, and U Kang, "Accurate Node Feature Estimation with Structured Variational Graph Autoencoder", ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2022, Washington DC. [PDF] [BIBTEX] [HOMEPAGE]
  • Tairen Piao and U Kang, "SensiMix: Sensitivity-Aware 8-bit Index & 1-bit Value Mixed Precision Quantization for BERT Compression", PLOS ONE (PLOS ONE), 2022 [PDF] [BIBTEX] [HOMEPAGE]
  • Jinhong Jung, Jaemin Yoo, and U Kang, "Signed Random Walk Diffusion for Effective Representation Learning in Signed Graphs", PLOS ONE (PLOS ONE), 2022 [PDF] [BIBTEX] [HOMEPAGE]
  • Ikhyun Cho and U Kang, "Pea-KD: Parameter-efficient and accurate Knowledge Distillation on BERT", PLOS ONE (PLOS ONE), 2022. [PDF]
  • Jaemin Yoo, Sooyeon Shim, and U Kang, "Model-Agnostic Augmentation for Accurate Graph Classification", The Web Conference (WWW), 2022, Online. [PDF] [BIBTEX] [HOMEPAGE]
  • Jaemin Yoo and U Kang, "Attention-Based Autoregression for Accurate and Efficient Multivariate Time Series Forecasting", SIAM International Conference on Data Mining (SDM), 2021, Alexandria, Virginia, USA (Virtual Event). [PDF] [BIBTEX]
  • Huiwen Xu and U Kang, "Transfer Alignment Network for Blind Unsupervised Domain Adaptation", Knowledge and Information Systems (KAIS), 2021 [PDF]
  • Dawon Ahn, Jun-gi Jang, and U Kang, "Time-Aware Tensor Decomposition for Sparse Tensors", Machine Learning (Machine Learning), 2021 [PDF] [BIBTEX]
  • Jaemin Yoo, Junghun Kim, Hoyoung Yoon, and U Kang, "Accurate Graph-Based PU Learning without Class Prior", IEEE International Conference on Data Mining (ICDM), 2021, Auckland (virtual event). [PDF] [BIBTEX]
  • Hyunsik Jeon, Seongmin Lee, and U Kang, "Unsupervised Multi-Source Domain Adaptation with No Observable Source Data", PLOS ONE (PLOS ONE), 2021 [PDF] [BIBTEX] [HOMEPAGE]
  • Hyun Dong Lee, Seongmin Lee, and U Kang, "AUBER: Automated BERT Regularization", PLOS ONE (PLOS ONE), 2021 [PDF] [BIBTEX] [HOMEPAGE]
  • Jaehun-Jung, Jinhong Jung, and U Kang, "Learning to Walk across Time for Interpretable Temporal Knowledge Graph Completion", The 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) 2021 [PDF]
  • Jaemin Yoo, Yejun Soun, Yong-chan Park, and U Kang, "Accurate Multivariate Stock Movement Prediction via Data-Axis Transformer with Multi-Level Contexts", ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2021, Singapore (Virtual Event). [PDF] [BIBTEX]
  • Jaemin Yoo and U Kang, "Attention-Based Autoregression for Accurate and Efficient Multivariate Time Series Forecasting", SIAM International Conference on Data Mining (SDM), 2021, Alexandria, Virginia, USA (Virtual Event). [PDF] [BIBTEX]
  • Junghun Kim, Jinhong Jung, and U Kang, "Compressing Deep Graph Convolution Network with Multi-Staged Knowledge Distillation", PLOS ONE (PLOS ONE), 2021 [PDF] [BIBTEX] [HOMEPAGE]
  • Seongmin Lee, Hyunsik Jeon, and U Kang, "Multi-EPL: Accurate multi-source domain adaptation", PLOS ONE (PLOS ONE), 2021 [PDF] [BIBTEX] [HOMEPAGE]
  • Vladimir Egay and U Kang, "Accurate Company-Related News Extraction", Korean Software Congress, 2021, 휘닉스 평창 호텔. [PDF]
  • Jaemin Yoo and U Kang, "Sampling Subgraphs with Guaranteed Treewidth for Accurate and Efficient Graphical Inference", ACM International WSDM Conference (WSDM), 2020, Houston, Texas, USA. [PDF] [BIBTEX] [HOMEPAGE]
  • Jaemin Yoo, Minyong Cho, Taebum Kim, and U Kang, "Knowledge Extraction with No Observable Data", Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019, Vancouver, Canada. [BIBTEX] [HOMEPAGE] [PDF]
  • Seung Cheol Park, Shuyu Wang, Hunjung Lim, and U Kang, "Curved-Voxel Clustering for Accurate Segmentation of 3D LIDAR Point Clouds with Real Time Performance", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2019, Macao, China. [PDF] [BIBTEX]
  • Yang Bai, Hyun Dong Lee, and U Kang, "Remaining Useful Life Prediction Using LSTM Model with Attention", Korean Institute of Information Scientists and Engineers Winter Conference 2019
  • Jamin Yoo, Hyunsik Jeon, and U Kang, "Belief Propagation Network for Hard Inductive Semi-supervised Learning", 28th International Joint Conference on Artificial Intelligence (IJCAI) 2019, Macao, China. [BIBTEX] [HOMEPAGE] [PDF]
  • Eunjeong Kang, Minsu Park, Peonggang Park, Namyong Park, Younglee Jung, U Kang, Hee Kyung Kang, Dong Ki Kim, Kwon Wook Joo, Yon Su Kim, Hyung Jin Yoon and Hajeong Lee, "Acute kidney injury predicts all-cause mortality in patients with cancer", Cancer Medicine (Cancer Medicine), 2019. [PDF]
  • Woojung Jin, Dongjin Choi, YoungJin Kim, and U Kang, "Activity Prediction from Sensor Data using Convolutional Neural Networks and an Efficient Compression Method", Journal of Korean Institute of Information Scientists and Engineers, vol.45, no.6, pp.564-571, June 2018
  • Namyong Park, Eunjeong Kang, Minsu Park, Hajeong Lee, Hee-Gyung Kang, Hyung-Jin Yoon, and U Kang, "Predicting acute kidney injury in cancer patients using heterogeneous and irregular data", PLOS ONE, 2018. [PDF] [BIBTEX]
  • Mauro Scanagatta, Giorgio Corani, Marco Zaffalon, Jaemin Yoo, and U Kang, "Efficient Learning of Bounded-Treewidth Bayesian Networks from Complete and Incomplete Data Sets", International Journal of Approximate Reasoning (IJAR), 2018. [PDF] [BIBTEX]
  • Junghwan Kim, Haekyu Park, Ji-Eun Lee, and U Kang, "SIDE: Representation Learning in Signed Directed Networks", The Web Conference (WWW) 2018, Lyon, France. [BIBTEX] [HOMEPAGE] [PDF]
  • Saehan Jo, Jaemin Yoo, and U Kang, "Fast and Scalable Distributed Loopy Belief Propagation on Real-World Graphs", 11th ACM International Conference on Web Search and Data Mining (WSDM) 2018, Los Angeles, CA, USA. [BIBTEX] [HOMEPAGE (CODE, DATA)] [PDF]
  • Jaemin Yoo, Saehan Jo, and U Kang, "Supervised Belief Propagation: Scalable Supervised Inference on Attributed Networks", IEEE International Conference on Data Mining (ICDM) 2017, New Orleans, USA. [BIBTEX] [HOMEPAGE (CODE, DATA)] [PDF]
  • Kyung-Min Kim, Jinhong Jung, Jihee Ryu, Ha-Myung Park, Joseph P.Joohee, Seokwoo Jeong, U Kang, and Sung-Hyon Myaeng, "A New Question Answering Approach with Conceptual Graphs", Conférence en Recherche d’Information et Applications (CORIA) 2017, Marseille, France. [BIBTEX] [PDF]
  • Min-Hee Jang, Christos Faloutsos, Sang-Wook Kim, U Kang, and Jiwoon Ha, "PIN-TRUST: Fast Trust Propagation Exploiting Positive, Implicit, and Negative Information", ACM International Conference on Information and Knowledge Management (CIKM) 2016, Indianapolis, Indiana, USA. [BIBTEX] [PDF]
  • Dongyeop Kang, Woosang Lim, Kijung Shin, Lee Sael, and U Kang, "Data/Feature Distributed Stochastic Coordinate Descent for Logistic Regression", 23rd ACM International Conference on Information and Knowledge Management (CIKM) 2014, Shaghai, China [BIBTEX] [PDF] [SUPPLEMENTARY DOCUMENT]
  • U Kang, Martial Hebert, and Soonyong Park, "Fast and Scalable Approximate Spectral Graph Matching for Correspondence Problems", Information Sciences, 2013. [BIBTEX] [PDF]
  • U Kang, Hanghang Tong, and Jimeng Sun, "Fast Random Walk Graph Kernel", SIAM International Conference on Data Mining (SDM) 2012, Anaheim, California, USA. (acceptance rate 27 %) [BIBTEX] [PDF]
  • Danai Koutra, Tai-You Ke, U Kang, Duen Horng (Polo) Chau, Hsing-Kuo Kenneth Pao, and Christos Faloutsos, "Unifying Guilt-by-Association Approaches: Theorems and Fast Algorithms", European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2011, Athens, Greece. (acceptance rate 20.2 %) [BIBTEX] [PDF]
  • Robson L. F. Cordeiro, Caetano Traina Jr., Agma J. M. Traina, Julio Lopez, U Kang, and Christos Faloutsos, "Clustering Very Large Multi-dimensional Datasets with MapReduce", ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2011, San Diego, CA, USA. (acceptance rate 17.5 %) [BIBTEX] [PDF]
  • U Kang, Duen Horng "Polo" Chau, and Christos Faloutsos, "Inference of Beliefs on Billion-Scale Graphs", Large-scale Data Mining: Theory and Applications (LDMTA) 2010, in conjunction with KDD 2010, Washington D.C., USA. [BIBTEX] [PDF]