发表机构
Illinois Institute of Technology（伊利诺伊理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SaCRL框架，无需先验结构知识即可联合识别因果结构并学习不变表示，通过HSIC软优化实现结构选择，在多个基准上取得最优性能。
AI 中文摘要
因果表示学习旨在通过利用数据生成背后的因果结构来发现鲁棒特征。现有方法需要预先指定因果结构，然而不同的结构要求根本不相容的不变性约束，且错误设定会导致表示丢弃预测信息。我们提出SaCRL，一个无需先验结构知识即可联合识别因果结构并学习相应不变表示的框架。我们的方法将结构选择表述为基于HSIC的违反度量的候选不变性上的软优化，并采用自适应权重自动集中于可实现的结构。我们提供了结构识别的理论保证，包括随机特征近似下的结构识别、不变性满足以及分布外泛化。实验上，SaCRL在合成和半合成的贝叶斯网络基准上恢复了真实结构，在Colored MNIST上优于固定不变性基线，在三个DomainBed基准（PACS、VLCS、OfficeHome）上达到了最先进的准确率，并在结构错误设定和有限环境多样性下优雅地退化。代码可在以下网址获取：this https URL。
英文摘要
Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the causal structure a priori, yet different structures demand fundamentally incompatible invariance constraints, and misspecification leads to representations that discard predictive information. We introduce SaCRL, a framework that jointly identifies the causal structure and learns the corresponding invariant representation without prior structural knowledge. Our approach formulates structure selection as a soft optimization over candidate invariances using HSIC-based violation metrics, with adaptive weights that automatically concentrate on the achievable structure. We provide theoretical guarantees for structure identification, including under random-feature approximation, invariance satisfaction, and out-of-distribution generalization. Empirically, SaCRL recovers the true structure on synthetic and semi-synthetic Bayesian-network benchmarks, outperforms fixed-invariance baselines on Colored MNIST, achieves state-of-the-art accuracy on three DomainBed benchmarks (PACS, VLCS, OfficeHome), and degrades gracefully under structural misspecification and limited environment diversity. Code is available at: https://github.com/ArmanBehnam/sacrl.
