Scalable Joint Models for Reliable Uncertainty-Aware Event Prediction

被引:27
|
作者
Soleimani, Hossein [1 ]
Hensman, James [2 ]
Saria, Suchi [1 ]
机构
[1] Johns Hopkins Univ, Dept Comp Sci, Baltimore, MD 21218 USA
[2] Univ Lancaster, Div Med, Lancaster LA1 4YB, England
基金
美国国家科学基金会;
关键词
Uncertainty-aware prediction; missing data; scalable Gaussian processes; survival analysis; joint modeling; time series; THERAPY; RISK;
D O I
10.1109/TPAMI.2017.2742504
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Missing data and noisy observations pose significant challenges for reliably predicting events from irregularly sampled multivariate time series (longitudinal) data. Imputation methods, which are typically used for completing the data prior to event prediction, lack a principled mechanism to account for the uncertainty due to missingness. Alternatively, state-of-the-art joint modeling techniques can be used for jointly modeling the longitudinal and event data and compute event probabilities conditioned on the longitudinal observations. These approaches, however, make strong parametric assumptions and do not easily scale to multivariate signals with many observations. Our proposed approach consists of several key innovations. First, we develop a flexible and scalable joint model based upon sparse multiple-output Gaussian processes. Unlike state-of-the-art joint models, the proposed model can explain highly challenging structure including non-Gaussian noise while scaling to large data. Second, we derive an optimal policy for predicting events using the distribution of the event occurrence estimated by the joint model. The derived policy trades-off the cost of a delayed detection versus incorrect assessments and abstains from making decisions when the estimated event probability does not satisfy the derived confidence criteria. Experiments on a large dataset show that the proposed framework significantly outperforms state-of-the-art techniques in event prediction.
引用
收藏
页码:1948 / 1963
页数:16
相关论文
共 50 条
  • [1] Uncertainty-Aware Attention for Reliable Interpretation and Prediction
    Heo, Jay
    Lee, Hae Beom
    Kim, Saehoon
    Lee, Juho
    Kim, Kwang Joon
    Yang, Eunho
    Hwang, Sung Ju
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [2] Uncertainty-Aware Reliable Text Classification
    Hu, Yibo
    Khan, Latifur
    [J]. KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 628 - 636
  • [3] Learning Adaptive Probabilistic Models for Uncertainty-Aware Air Pollution Prediction
    Wu, Zhiyuan
    Liu, Ning
    Li, Guodong
    Liu, Xinyu
    Wang, Yue
    Zhang, Lin
    [J]. IEEE ACCESS, 2023, 11 : 24971 - 24985
  • [4] Uncertain FlexOffers: a scalable, uncertainty-aware model for energy flexibility
    Lilliu, Fabio
    Pedersen, Torben Bach
    Siksnys, Laurynas
    Neupane, Bijay
    [J]. PROCEEDINGS OF THE 2023 THE 14TH ACM INTERNATIONAL CONFERENCE ON FUTURE ENERGY SYSTEMS, E-ENERGY 2023, 2023, : 30 - 41
  • [5] CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization
    Moreau, Arthur
    Piasco, Nathan
    Tsishkou, Dzmitry
    Stanciulescu, Bogdan
    de la Fortelle, Arnaud
    [J]. 2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, : 1848 - 1857
  • [6] Uncertainty-aware Flexibility Envelope Prediction in Buildings with Controller-agnostic Battery Models
    Scharnhorst, Paul
    Schubnel, Baptiste
    Carrillo, Rafael E.
    Alet, Pierre-Jean
    Jones, Colin N.
    [J]. 2023 AMERICAN CONTROL CONFERENCE, ACC, 2023, : 583 - 590
  • [7] Uncertainty-Aware Yield Prediction with Multimodal Molecular Features
    Chen, Jiayuan
    Guo, Kehan
    Liu, Zhen
    Isayev, Olexandr
    Zhang, Xiangliang
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 8, 2024, : 8274 - 8282
  • [8] Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections
    Huang, Xin
    McGill, Stephen G.
    Williams, Brian C.
    Fletcher, Luke
    Rosman, Guy
    [J]. 2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2019, : 9718 - 9724
  • [9] Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
    Chauhan, Lakshay
    Alberg, John
    Lipton, Zachary C.
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [10] Poster: Uncertain FlexOffers, a scalable, uncertainty-aware model for energy flexibility
    Lilliu, Fabio
    Pedersen, Torben Bach
    Siksnys, Laurynas
    Neupane, Bijay
    [J]. PROCEEDINGS OF THE 2022 THE THIRTEENTH ACM INTERNATIONAL CONFERENCE ON FUTURE ENERGY SYSTEMS, E-ENERGY 2022, 2022, : 448 - 449