关于域内泛化中因果性的视角转变
机器学习
2025-08-19 v1 人工智能
计算机视觉与模式识别
摘要
因果建模能够导致鲁棒AI泛化的承诺近期在域内泛化（DG）基准测试中受到挑战。我们重新审视了因果与DG文献中的论点，调和表面矛盾，提出更细致的关于因果在泛化中作用的理论。我们还提供了一个交互式演示，访问地址为 https://chai-uk.github.io/ukairs25-causal-predictors/。
引用
@article{arxiv.2508.12798,
title = {A Shift in Perspective on Causality in Domain Generalization},
author = {Damian Machlanski and Stephanie Riley and Edward Moroshko and Kurt Butler and Panagiotis Dimitrakopoulos and Thomas Melistas and Akchunya Chanchal and Steven McDonagh and Ricardo Silva and Sotirios A. Tsaftaris},
journal= {arXiv preprint arXiv:2508.12798},
year = {2025}
}
备注
2 pages, 1 figure, to be presented at the UK AI Research Symposium (UKAIRS) 2025