Invariant Models for Causal Transfer Learning

被引:0
|
作者
Rojas-Carulla, Mateo [1 ,2 ]
Schoelkopf, Bernhard [1 ]
Turner, Richard [2 ]
Peters, Jonas [1 ,3 ]
机构
[1] Max Planck Inst Intelligent Syst, Tubingen, Germany
[2] Univ Cambridge, Dept Engn, Cambridge, England
[3] Univ Copenhagen, Dept Math Sci, Copenhagen, Denmark
基金
英国工程与自然科学研究理事会;
关键词
Transfer learning; Multi-task learning; Causality; Domain adaptation; Domain generalization; INFERENCE; NETWORKS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true for a subset of predictor variables: the conditional distribution of the target variable given this subset of predictors is invariant over all tasks. We show how this assumption can be motivated from ideas in the field of causality. We focus on the problem of Domain Generalization, in which no examples from the test task are observed. We prove that in an adversarial setting using this subset for prediction is optimal in Domain Generalization; we further provide examples, in which the tasks are sufficiently diverse and the estimator therefore outperforms pooling the data, even on average. If examples from the test task are available, we also provide a method to transfer knowledge from the training tasks and exploit all available features for prediction. However, we provide no guarantees for this method. We introduce a practical method which allows for automatic inference of the above subset and provide corresponding code. We present results on synthetic data sets and a gene deletion data set.
引用
收藏
页数:34
相关论文
共 50 条
  • [41] Causal deep learning models for studying the Earth system
    Tesch, Tobias
    Kollet, Stefan
    Garcke, Jochen
    GEOSCIENTIFIC MODEL DEVELOPMENT, 2023, 16 (08) : 2149 - 2166
  • [42] Active learning for optimal intervention design in causal models
    Zhang, Jiaqi
    Cammarata, Louis
    Squires, Chandler
    Sapsis, Themistoklis P.
    Uhler, Caroline
    NATURE MACHINE INTELLIGENCE, 2023, 5 (10) : 1066 - +
  • [43] A Developmental Approach to Learning Causal Models for Cyber Security
    Mugan, Jonathan
    MACHINE INTELLIGENCE AND BIO-INSPIRED COMPUTATION: THEORY AND APPLICATIONS VII, 2013, 8751
  • [44] Discovering Causal Models of Self-Regulated Learning
    Brokenshire, David
    Kumar, Vive
    ARTIFICIAL INTELLIGENCE IN EDUCATION: BUILDING LEARNING SYSTEMS THAT CARE: FROM KNOWLEDGE REPRESENTATION TO AFFECTIVE MODELLING, 2009, 200 : 257 - +
  • [45] Beyond the information given: Causal models in learning and reasoning
    Waldmann, Michael R.
    Hagmayer, York
    Blaisdell, Aaron P.
    CURRENT DIRECTIONS IN PSYCHOLOGICAL SCIENCE, 2006, 15 (06) : 307 - 311
  • [46] Learning the Causal Structure of Copula Models with Latent Variables
    Cui, Ruifei
    Groot, Perry
    Schauer, Moritz
    Heskes, Tom
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2018, : 188 - 197
  • [47] Causal ABMs: Learning Plausible Causal Models using Agent-based Modeling
    Valogianni, Konstantina
    Padmanabhan, Balaji
    KDD'22 WORKSHOP ON CAUSAL DISCOVERY, VOL 185, 2022, 185 : 3 - 28
  • [48] Transfer and transport: incorporating causal methods for improving predictive models
    Singleton, Kyle W.
    Bui, Alex A. T.
    Hsu, William
    JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2014, 21 (E2) : E374 - E375
  • [49] Transfer Learning in Multi-Armed Bandit: A Causal Approach
    Zhang, Junzhe
    Bareinboim, Elias
    AAMAS'17: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2017, : 1778 - 1780
  • [50] Answering Binary Causal Questions: A Transfer Learning Based Approach
    Kayesh, Humayun
    Islam, Md Saiful
    Wang, Junhu
    Anirban, Shikha
    Kayes, A. S. M.
    Wafters, Paul
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,