arXiv：cs.LG· Arman Behnam, Binghui Wang·· 2 天前AI 评分39
SaCRL：无需先验结构的因果表示学习框架
Structure-agnostic Causal Representation Learning
AI 导读
SaCRL 是一个无需先验因果结构知识、可联合识别因果结构与学习不变表示的框架，通过基于 HSIC 的违反度量对候选不变性做软优化，并自适应聚焦可达结构。它在合成与半合成贝叶斯网络基准上恢复真实结构，在 Colored MNIST 上超越固定不变性基线，并在 PACS、VLCS、OfficeHome 三个 DomainBed 基准上取得 SOTA 准确率。代码已开源。
正文
Abstract: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: this https URL.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.00968 [cs.LG] |
| (or arXiv:2610.00968v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00968 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Arman Behnam [view email]
[v1]
Thu, 1 Oct 2026 02:59:02 UTC (73 KB)
来源：arXiv：cs.LG · arxiv.org