Publications

* denotes equal contribution, denotes corresponding author.

2024

  1. AAAI-24
    DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency
    W. Yao* , K. Yin* , W. K. Cheung , J. Liu , and J. Qin
    In Proceedings of the AAAI Conference on Artificial Intelligence , 2024
    Acceptance ratio: 2342⁄9862 = 23.75%

2023

  1. ACM TIST
    Adaptive Integration of Categorical and Multi-relational Ontologies with EHR Data for Medical Concept Embedding
    C. W. Cheong , K. Yin , W. K. Cheung , B. C. Fung , and J. Poon
    ACM Transactions on Intelligent Systems and Technology, 2023
  2. IEEE TKDE
    PATNet: Propensity-Adjusted Temporal Network for Joint Imputation and Prediction Using Binary EHRs With Observation Bias
    K. Yin , D. Qian , and W. K. Cheung
    IEEE Transactions on Knowledge and Data Engineering, 2023

2022

  1. IEEE TKDE
    Learning Inter-Modal Correspondence and Phenotypes From Multi-Modal Electronic Health Records
    K. Yin , W. K. Cheung , B. C. Fung , and J. Poon
    IEEE Transactions on Knowledge and Data Engineering, 2022

2021

  1. AAAI-21
    SWIFT: Scalable Wasserstein factorization for sparse nonnegative tensors
    A. Afshar , K. Yin , S. Yan , C. Qian , J. Ho , H. Park , and J. Sun
    In Proceedings of the AAAI Conference on Artificial Intelligence , 2021
    Acceptance ratio: 1692⁄7911 = 21.4%
  2. SDM-21
    TedPar: Temporally dependent PARAFAC2 factorization for phenotype-based disease progression modeling
    K. Yin , W. K. Cheung , B. C. Fung , and J. Poon
    In Proceedings of the 2021 SIAM International Conference on Data Mining (SDM) , 2021
    Acceptance ratio: 85⁄400 = 21.25%

2020

  1. KDD-20
    LogPar: Logistic PARAFAC2 factorization for temporal binary data with missing values
    K. Yin , A. Afshar , J. C. Ho , W. K. Cheung , C. Zhang , and J. Sun
    In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , 2020
    Research Track; acceptance ratio: 216⁄1279 = 16.9%
  2. JHIR
    Context-aware time series imputation for multi-analyte clinical data
    K. Yin , L. Feng , and W. K. Cheung
    Journal of Healthcare Informatics Research, 2020
    This is an extension of our previous two-page abstract appeared in ICHI-19.

2019

  1. AAAI-19
    Learning phenotypes and dynamic patient representations via RNN regularized collective non-negative tensor factorization
    K. Yin , D. Qian , W. K. Cheung , B. C. Fung , and J. Poon
    In Proceedings of the AAAI Conference on Artificial Intelligence , 2019
    Acceptance ratio: 1150⁄7095 = 16.2%
  2. IJCAI-19
    Medical Concept Embedding with Multiple Ontological Representations
    L. Song , C. W. Cheong , K. Yin , W. K. Cheung , B. C. M. Fung , and J. Poon
    In Proceedings of the 28th International Joint Conference on Artificial Intelligence , 2019
    Acceptance ratio: 850⁄4752 = 17.9%
  3. ICHI-19
    Context-aware imputation for clinical time series
    K. Yin , and W. K. Cheung
    In 2019 IEEE International Conference on Healthcare Informatics (ICHI) , 2019
    Challenge track; two-page abstract

2018

  1. IJCAI-18
    Joint Learning of Phenotypes and Diagnosis-Medication Correspondence via Hidden Interaction Tensor Factorization.
    K. Yin , W. K. Cheung , Y. Liu , B. C. M. Fung , and J. Poon
    In Proceedings of the 27th International Joint Conference on Artificial Intelligence , 2018
    Acceptance ratio: 710⁄3470 = 20%