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
[31]   Eco-FL: Adaptive Federated Learning with Efficient Edge Collaborative Pipeline Training [J].
Ye, Shengyuan ;
Zeng, Liekang ;
Wu, Qiong ;
Luo, Ke ;
Fang, Qingze ;
Chen, Xu .
51ST INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, ICPP 2022, 2022,
[32]   Inferring the heterogeneous effect of urban land use on building height with causal machine learning [J].
Chen, Yimin ;
Chen, Jing ;
Zhao, Shuai ;
Xu, Xiaocong ;
Liu, Xiaoping ;
Zhang, Xinchang ;
Zhang, Honghui .
GISCIENCE & REMOTE SENSING, 2024, 61 (01)
[33]   Towards human-like perception: Learning structural causal model in heterogeneous graph [J].
Lin, Tianqianjin ;
Song, Kaisong ;
Jiang, Zhuoren ;
Kang, Yangyang ;
Yuan, Weikang ;
Li, Xurui ;
Sun, Changlong ;
Huang, Cui ;
Liu, Xiaozhong .
INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (02)
[34]   Split-Treatment Analysis to Rank Heterogeneous Causal Effects for Prospective Interventions [J].
Xu, Yanbo ;
Mahajan, Divyat ;
Manrao, Liz ;
Sharma, Amit ;
Kiciman, Emre .
WSDM '21: PROCEEDINGS OF THE 14TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2021, :409-417
[35]   Causal interaction trees: Finding subgroups with heterogeneous treatment effects in observational data [J].
Yang, Jiabei ;
Dahabreh, Issa J. ;
Steingrimsson, Jon A. .
BIOMETRICS, 2022, 78 (02) :624-635
[36]   Estimating heterogeneous causal effects in observational studies using small area predictors [J].
Ranjbar, Setareh ;
Salvati, Nicola ;
Pacini, Barbara .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2023, 184
[37]   Learning Individual Causal Effects from Networked Observational Data [J].
Guo, Ruocheng ;
Li, Jundong ;
Liu, Huan .
PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM '20), 2020, :232-240
[38]   Estimating Identifiable Causal Effects through Double Machine Learning [J].
Jung, Yonghan ;
Tian, Jin ;
Bareinboim, Elias .
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 :12113-12122
[39]   Learning Causal Effects via Weighted Empirical Risk Minimization [J].
Jung, Yonghan ;
Tian, Jin ;
Bareinboim, Elias .
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
[40]   Causal Effects of Motor Control on Gait Kinematics After Orthopedic Surgery in Cerebral Palsy: A Machine-Learning Approach [J].
Steele, Katherine M. ;
Schwartz, Michael H. .
FRONTIERS IN HUMAN NEUROSCIENCE, 2022, 16