mlsanityData to 7 Oct 2026

Transfer Learning for Individual Treatment Effect Estimation

arXiv 2210.00380 ↗First posted 1 Oct 2022cs.LG stat.ME stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

This work considers the problem of transferring causal knowledge between tasks for Individual Treatment Effect (ITE) estimation. To this end, we theoretically assess the feasibility of transferring ITE knowledge and present a practical framework for efficient transfer. A lower bound is introduced on the ITE error of the target task to demonstrate that ITE knowledge transfer is challenging due to the absence of counterfactual information. Nevertheless, we establish generalization upper bounds on the counterfactual loss and ITE error of the target task, demonstrating the feasibility of ITE knowledge transfer. Subsequently, we introduce a framework with a new Causal Inference Task Affinity (CITA) measure for ITE knowledge transfer. Specifically, we use CITA to find the closest source task to the target task and utilize it for ITE knowledge transfer. Empirical studies are provided, demonstrating the efficacy of the proposed method. We observe that ITE knowledge transfer can significantly (up to 95%) reduce the amount of data required for ITE estimation.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 27 of its 55 references that are in the map. First posted on arXiv 1 Oct 2022.

Builds on

27 of 55 references.

References · 27

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2019Invariant Risk Minimizationcited by 1,832
  3. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  4. 2016Progressive Neural Networkscited by 1,332
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  6. 2018Recognition in Terra Incognitacited by 655
  7. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  8. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  9. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 597
  10. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  11. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  12. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
15 more
  1. 2016Learning Representations for Counterfactual Inferencecited by 327
  2. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  3. 2015Recursive Partitioning for Heterogeneous Causal Effectscited by 254
  4. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 156
  5. 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 149
  6. 2020Deep Visual Domain Adaptationcited by 91
  7. 2019Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learningcited by 86
  8. 2020A Survey on Transfer Learning in Natural Language Processingcited by 33
  9. 2019Zero-Shot Task Transfercited by 26
  10. 2020Multi-task Causal Learning with Gaussian Processescited by 14
  11. 2021Task Affinity with Maximum Bipartite Matching in Few-Shot Learningcited by 8
  12. 2021Fisher Task Distance and Its Application in Neural Architecture Searchcited by 7
  13. 2020Task-Aware Neural Architecture Searchcited by 5
  14. 2019Supervised Encoding for Discrete Representation Learningcited by 3
  15. 2021Improved Automated Machine Learning from Transfer Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 3.

5 papers.

  1. 2023Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimationcited by 11
  2. 2024An adaptive transfer learning perspective on classification in non-stationary environmentscited by 0
  3. 2025Synergizing Deconfounding and Temporal Generalization For Time-series Counterfactual Outcome Estimationcited by 0
  4. 2025Task-Aware Multi-Expert Architecture For Lifelong Deep Learningcited by 0
  5. 2025Advantages and limitations in the use of transfer learning for individual treatment effects in causal machine learningcited by 0