arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.07032cs.LGcs.AI
收藏

缓解因果结构学习中的先验错误:一种基于贝叶斯网络的鲁棒方法

Mitigating Prior Errors in Causal Structure Learning: A Resilient Approach via Bayesian Networks

University of Science and Technology of China(中国科学技术大学)

Lyuzhou Chen, Taiyu Ban, Xiangyu Wang, Derui Lyu, Huanhuan Chen

AI总结:

针对因果结构学习中现有先验知识方法对先验错误鲁棒性不足的问题,提出基于准环识别的事后鲁棒策略,可减少人工干预,有效抵御边级先验错误尤其是反向错误,同时保留大部分正确先验。

摘要:

因果结构学习(CSL)是一种通过贝叶斯网络(BNs)编码变量间因果关系的重要技术。仅从数据中恢复因果结构颇具挑战,而整合能揭示部分结构真相的先验知识可显著提升学习质量。但现有基于先验知识的方法对先验中的错误鲁棒性有限:硬约束方法会完全忽略先验,软约束方法则基于预设置信度接受先验,这可能需要专家干预。为解决该问题,我们提出一种对因果结构学习中边级别先验错误具备鲁棒性的策略,以最大程度减少人工干预。我们将先验错误分为不同类型,并在数据充足的假设下,给出了其对结构汉明距离(SHD)的理论影响。有趣的是,我们发现并证明先验错误的强危害性与一种被定义为“准环”的独特无环闭合结构相关。基于这一洞见,我们采用一种事后策略,通过先验错误对“准环”数量增长的影响来识别这类错误。通过在真实数据集和合成数据集上的实证评估,我们证明了该策略对先验错误的鲁棒性。具体而言,我们强调其在保留大部分正确先验的同时,抵御反向错误的强大能力。

英文摘要:

Causal structure learning (CSL), a prominent technique for encoding cause-and-effect relationships among variables, through Bayesian Networks (BNs). Although recovering causal structure solely from data is a challenge, the integration of prior knowledge, revealing partial structural truth, can markedly enhance learning quality. However, current methods based on prior knowledge exhibit limited resilience to errors in the prior, with hard constraint methods disregarding priors entirely, and soft constraints accepting priors based on a predetermined confidence level, which may require expert intervention. To address this issue, we propose a strategy resilient to edge-level prior errors for CSL, thereby minimizing human intervention. We classify prior errors into different types and provide their theoretical impact on the Structural Hamming Distance (SHD) under the presumption of sufficient data. Intriguingly, we discover and prove that the strong hazard of prior errors is associated with a unique acyclic closed structure, defined as ``quasi-circle''. Leveraging this insight, a post-hoc strategy is employed to identify the prior errors by its impact on the increment of ``quasi-circles''. Through empirical evaluation on both real and synthetic datasets, we demonstrate our strategy's robustness against prior errors. Specifically, we highlight its substantial ability to resist order-reversed errors while maintaining the majority of correct prior.

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。

↑