Prediction with Incomplete Data under Agnostic Mask Distribution Shift

被引:0
|
作者
Zhu, Yichen [1 ]
Yuan, Jian [1 ]
Jiang, Bo [1 ]
Lin, Tao [2 ]
Jin, Haiming [1 ]
Wang, Xinbing [1 ]
Zhou, Chenghu [1 ]
机构
[1] Shanghai Jiao Tong Univ, Shanghai, Peoples R China
[2] Commun Univ China, Beijing, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Data with missing values is ubiquitous in many applications. Recent years have witnessed increasing attention on prediction with only incomplete data consisting of observed features and a mask that indicates the missing pattern. Existing methods assume that the training and testing distributions are the same, which may be violated in real-world scenarios. In this paper, we consider prediction with incomplete data in the presence of distribution shift. We focus on the case where the underlying joint distribution of complete features and label is invariant, but the missing pattern, i.e., mask distribution may shift agnostically between training and testing. To achieve generalization, we leverage the observation that for each mask, there is an invariant optimal predictor. To avoid the exponential explosion when learning them separately, we approximate the optimal predictors jointly using a double parameterization technique. This has the undesirable side effect of allowing the learned predictors to rely on the intra-mask correlation and that between features and mask. We perform decorrelation to minimize this effect. Combining the techniques above, we propose a novel prediction method called StableMiss. Extensive experiments on both synthetic and real-world datasets show that StableMiss is robust and outperforms state-of-the-art methods under agnostic mask distribution shift.
引用
收藏
页码:4720 / 4728
页数:9
相关论文
共 50 条
  • [1] Stable Prediction with Model Misspecification and Agnostic Distribution Shift
    Kuang, Kun
    Xiong, Ruoxuan
    Cui, Peng
    Athey, Susan
    Li, Bo
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 4485 - 4492
  • [2] Feature selection for quality prediction under distribution shift
    Liu, Wenyi
    Yairi, Takehisa
    Tamai, Nana
    [J]. 2022 61ST ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS (SICE), 2022, : 548 - 552
  • [3] Stable Prediction on Graphs with Agnostic Distribution Shifts
    Zhang, Shengyu
    Tong, Yunze
    Kuang, Kun
    Feng, Fuli
    Qiu, Jiezhong
    Yu, Jin
    Zhao, Zhou
    Yang, Hongxia
    Zhang, Zhongfei
    Wu, Fei
    [J]. KDD'23 WORKSHOP ON CAUSAL DISCOVERY, PREDICTION AND DECISION, VOL 218, 2023, 218 : 49 - 74
  • [4] Polyester Melt Characteristic Viscosity Prediction Method Under Incomplete Data
    Bi, Jinmao
    Zhang, Peng
    Zhang, Jie
    Zhao, Chuncai
    Cui, Li
    [J]. Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University, 2024, 58 (04): : 534 - 544
  • [5] Robust Conformal Prediction for STL Runtime Verification under Distribution Shift
    Zhao, Yiqi
    Hoxha, Bardh
    Fainekos, Georgios
    Deshmukhl, Jyotirmoy V.
    Lindemann, Lars
    [J]. PROCEEDINGS 15TH ACM/IEEE INTERNATIONAL CONFERENCE ON CYBER-PHYSICAL SYSTEMS, ICCPS 2024, 2024, : 169 - 179
  • [6] Sequential prediction under incomplete feedback
    Lugosi, Gabor
    [J]. ARTIFICIAL INTELLIGENCE RESEARCH AND DEVELOPMENT, 2007, 163 : 3 - 5
  • [7] Polynomial prediction using incomplete data
    Harju, PT
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1997, 45 (03) : 768 - 770
  • [8] Federated Learning with Data-Agnostic Distribution Fusion
    Duan, Jian-hui
    Li, Wenzhong
    Lou, Derun
    Li, Ruichen
    Lu, Sanglu
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 8074 - 8083
  • [10] Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?
    Hoang Pham
    The-Anh Ta
    Liu, Shiwei
    Xiang, Lichuan
    Le, Dung D.
    Wen, Hongkai
    Long Tran-Thanh
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,