paper-with-me

홈 › Papers

Partial Transportability for Domain Generalization

2025-03-30 · Kasra Jalaldoust, Alexis Bellot, Elias Bareinboim

A fundamental task in AI is providing performance guarantees for predictions made in unseen domains. In practice, there can be substantial uncertainty about the distribution of new data, and corresponding variability in the performance of existing predictors. Building on the theory of partial identification and transportability, this paper introduces new results for bounding the value of a functional of the target distribution, such as the generalization error of a classifier, given data from source domains and assumptions about the data generating mechanisms, encoded in causal diagrams. Our contribution is to provide the first general estimation technique for transportability problems, adapting existing parameterization schemes such Neural Causal Models to encode the structural constraints necessary for cross-population inference. We demonstrate the expressiveness and consistency of this procedure and further propose a gradient-based optimization scheme for making scalable inferences in practice. Our results are corroborated with experiments.

📄 PDF Abstract BibTeX arXiv:2503.23605

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

Causal Transportability of Experiments on Controllable Subsets of Variables: z-Transportability

2013-09-26 · Sanghack Lee, Vasant Honavar

We introduce z-transportability, the problem of estimating the causal effect of a set of variables X on another set of variables Y in a target domain from experiments on any subset of controllable variables Z where Z is …

Adapting, Fast and Slow: On Few-Shot Transportability of Compositions

2025-12-28 · Kasra Jalaldoust, Elias Bareinboim arxiv

Generalization across domains requires stable structure that links the source and target distributions. Building on causal transportability theory, we study a sequential prediction setting in which the target predictor c…

Domain Adaptation

General Transportability of Soft Interventions: Completeness Results

2020-12-01 · NeurIPS 2020 12 · Juan Correa, Elias Bareinboim

The challenge of generalizing causal knowledge across different environments is pervasive in scientific explorations, including in AI, ML, and Data Science. Experiments are usually performed in one environment (e.g., in …

Causal Inference

Switching Contexts: Transportability Measures for NLP

2021-05-03 · IWCS (ACL) 2021 6 · Guy Marshall, Mokanarangan Thayaparan, Philip Osborne, Andre Freitas

This paper explores the topic of transportability, as a sub-area of generalisability. By proposing the utilisation of metrics based on well-established statistics, we are able to estimate the change in performance of NLP…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Natural Language Inference

Transportability from Multiple Environments with Limited Experiments: Completeness Results

2014-12-01 · NeurIPS 2014 12 · Elias Bareinboim, Judea Pearl

This paper addresses the problem of $mz$-transportability, that is, transferring causal knowledge collected in several heterogeneous domains to a target domain in which only passive observations and limited experimental …