arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.18052cs.LGcs.AIstat.ME
收藏

基于测度论的反因果表示学习

Measure-Theoretic Anti-Causal Representation Learning

Illinois Institute of Technology(伊利诺伊理工学院)

Arman Behnam, Binghui Wang

AI总结:

针对反因果场景下因果表示学习的独特挑战,提出基于测度论的ACIA双层框架,通过干预核适配不同干预、无需显式因果结构、适配高维数据且有分布外泛化理论保证,实验及理论验证其性能优于现有方法。

摘要:

反因果场景(标签导致特征而非相反)下的因果表示学习存在独特挑战,需要专门的方法。我们提出反因果不变抽象(Anti-Causal Invariant Abstractions,ACIA),这是一种用于反因果表示学习的新型测度论框架。ACIA采用双层设计:低层表示捕捉标签生成观测的方式,高层表示则学习跨环境特定变化的稳定因果模式。ACIA通过干预核适配完美与不完美干预,消除对显式因果结构的依赖,有效处理高维数据,并为分布外泛化提供理论保证,解决了现有方法的关键局限。在合成数据集和真实世界医疗数据集上的实验表明,ACIA在准确率和不变性指标上始终优于当前最优方法。此外,我们的理论结果给出了训练环境与未见环境之间性能差距的紧界,证实了该方法在鲁棒反因果学习中的有效性。

英文摘要:

Causal representation learning in the anti-causal setting (labels cause features rather than the reverse) presents unique challenges requiring specialized approaches. We propose Anti-Causal Invariant Abstractions (ACIA), a novel measure-theoretic framework for anti-causal representation learning. ACIA employs a two-level design, low-level representations capture how labels generate observations, while high-level representations learn stable causal patterns across environment-specific variations. ACIA addresses key limitations of existing approaches by accommodating prefect and imperfect interventions through interventional kernels, eliminating dependency on explicit causal structures, handling high-dimensional data effectively, and providing theoretical guarantees for out-of-distribution generalization. Experiments on synthetic and real-world medical datasets demonstrate that ACIA consistently outperforms state-of-the-art methods in both accuracy and invariance metrics. Furthermore, our theoretical results establish tight bounds on performance gaps between training and unseen environments, confirming the efficacy of our approach for robust anti-causal learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑