An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects

被引:0
|
作者
Vo, Thanh Vinh [1 ]
Bhattacharyya, Arnab [1 ]
Lee, Young [2 ,3 ]
Leong, Tze-Yun [1 ]
机构
[1] Natl Univ Singapore, Sch Comp, Singapore, Singapore
[2] Roche AG, Basel, Switzerland
[3] Harvard Univ, Cambridge, MA USA
来源
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022 | 2022年
基金
新加坡国家研究基金会;
关键词
INFERENCE;
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
We propose a new causal inference framework to learn causal effects from multiple, decentralized data sources in a federated setting. We introduce an adaptive transfer algorithm that learns the similarities among the data sources by utilizing Random Fourier Features to disentangle the loss function into multiple components, each of which is associated with a data source. The data sources may have different distributions; the causal effects are independently and systematically incorporated. The proposed method estimates the similarities among the sources through transfer coefficients, and hence requiring no prior information about the similarity measures. The heterogeneous causal effects can be estimated with no sharing of the raw training data among the sources, thus minimizing the risk of privacy leak. We also provide minimax lower bounds to assess the quality of the parameters learned from the disparate sources. The proposed method is empirically shown to outperform the baselines on decentralized data sources with dissimilar distributions.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] HETEROGENEOUS CAUSAL EFFECTS WITH IMPERFECT COMPLIANCE: A BAYESIAN MACHINE LEARNING APPROACH
    Bargagli-Stoffi, Falco J.
    de Witte, Kristof
    Gnecco, Giorgio
    ANNALS OF APPLIED STATISTICS, 2022, 16 (03): : 1986 - 2009
  • [2] Learning Nonlinear Causal Effects via Kernel Anchor Regression
    Shi, Wenqi
    Xu, Wenkai
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2023, 216 : 1942 - 1952
  • [3] Federated Learning of Generalized Linear Causal Networks
    Ye, Qiaoling
    Amini, Arash A.
    Zhou, Qing
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (10) : 6623 - 6636
  • [4] Inferring heterogeneous treatment effects of crashes on highway traffic: A doubly robust causal machine learning approach
    Li, Shuang
    Pu, Ziyuan
    Cui, Zhiyong
    Lee, Seunghyeon
    Guo, Xiucheng
    Ngoduy, Dong
    TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2024, 160
  • [5] A BAYESIAN MACHINE LEARNING APPROACH FOR ESTIMATING HETEROGENEOUS SURVIVOR CAUSAL EFFECTS: APPLICATIONS TO A CRITICAL CARE TRIAL
    Chen, Xinyuan
    Harhay, Michael O.
    Tong, Guangyu
    Li, Fan
    ANNALS OF APPLIED STATISTICS, 2024, 18 (01): : 350 - 374
  • [6] Machine learning estimation of heterogeneous causal effects: Empirical Monte Carlo evidence
    Knaus, Michael C.
    Lechner, Michael
    Strittmatter, Anthony
    ECONOMETRICS JOURNAL, 2021, 24 (01): : 134 - 161
  • [7] Kernel methods for causal functions: dose, heterogeneous and incremental response curves
    Singh, R.
    Xu, L.
    Gretton, A.
    BIOMETRIKA, 2024, 111 (02) : 497 - 516
  • [8] Instrument validity for heterogeneous causal effects
    Sun, Zhenting
    JOURNAL OF ECONOMETRICS, 2023, 237 (02)
  • [9] Bayesian Federated Estimation of Causal Effects from Observational Data
    Thanh Vinh Vo
    Lee, Young
    Trong Nghia Hoang
    Leong, Tze-Yun
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, VOL 180, 2022, 180 : 2024 - 2034
  • [10] Bayesian graphical modeling for heterogeneous causal effects
    Castelletti, Federico
    Consonni, Guido
    STATISTICS IN MEDICINE, 2023, 42 (01) : 15 - 32