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
  • [21] Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding
    Tang, Caizhi
    Wang, Huiyuan
    Li, Xinyu
    Cui, Qing
    Zhang, Ya-Lin
    Zhu, Feng
    Li, Longfei
    Zhou, Jun
    Jiang, Linbo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [22] Inferring individual direct causal effects under heterogeneous peer influence
    Adhikari, Shishir
    Zheleva, Elena
    MACHINE LEARNING, 2025, 114 (04)
  • [23] Robust Causal Learning for the Estimation of Average Treatment Effects
    Huang, Yiyan
    Leung, Cheuk Hang
    Wu, Qi
    Yan, Xing
    Ma, Shumin
    Yuan, Zhiri
    Wang, Dongdong
    Huang, Zhixiang
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [24] Automatic Debiased Machine Learning of Causal and Structural Effects
    Chernozhukov, Victor
    Newey, Whitney K.
    Singh, Rahul
    ECONOMETRICA, 2022, 90 (03) : 967 - 1027
  • [25] KERNEL BALANCING: A FLEXIBLE NON-PARAMETRIC WEIGHTING PROCEDURE FOR ESTIMATING CAUSAL EFFECTS
    Hazlett, Chad
    STATISTICA SINICA, 2020, 30 (03) : 1155 - 1189
  • [26] Eco-FL: Adaptive Federated Learning with Efficient Edge Collaborative Pipeline Training
    Ye, Shengyuan
    Zeng, Liekang
    Wu, Qiong
    Luo, Ke
    Fang, Qingze
    Chen, Xu
    51ST INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, ICPP 2022, 2022,
  • [27] An Approach for Estimating Causal Effects in Randomized Trials with Noncompliance
    Chiba, Yasutaka
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2010, 39 (12) : 2146 - 2156
  • [28] A Selection Bias Approach to Sensitivity Analysis for Causal Effects
    Blackwell, Matthew
    POLITICAL ANALYSIS, 2014, 22 (02) : 169 - 182
  • [29] Inferring the heterogeneous effect of urban land use on building height with causal machine learning
    Chen, Yimin
    Chen, Jing
    Zhao, Shuai
    Xu, Xiaocong
    Liu, Xiaoping
    Zhang, Xinchang
    Zhang, Honghui
    GISCIENCE & REMOTE SENSING, 2024, 61 (01)
  • [30] Towards human-like perception: Learning structural causal model in heterogeneous graph
    Lin, Tianqianjin
    Song, Kaisong
    Jiang, Zhuoren
    Kang, Yangyang
    Yuan, Weikang
    Li, Xurui
    Sun, Changlong
    Huang, Cui
    Liu, Xiaozhong
    INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (02)