arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.01942cs.LGstat.ML
收藏

高效解耦因果表示

Efficiently Disentangle Causal Representations

Yuanpeng Li, Joel Hestness, Mohamed Elhoseiny, Liang Zhao, Kenneth Church

AI总结:

本文提出一种基于条件概率差异和模型泛化能力的高效因果解耦表示学习方法,仅需评估泛化能力,在多种任务上比先前方法样本效率高1.9-11.0倍、速度快9.4-32.4倍。

摘要:

本文提出了一种高效的方法,基于原始分布和新分布中条件概率的差异来学习具有因果机制的解耦表示。我们利用模型的泛化能力来近似这一差异,使其符合标准机器学习框架并能高效计算。与依赖学习器对新分布适应速度的最先进方法相比,本文方法仅需评估模型的泛化能力。我们为该方法的优势提供了理论解释,实验表明,该技术在各种任务中比先前方法的样本效率高1.9--11.0倍,速度快9.4--32.4倍。源代码可在https://github.com/yuanpeng16/EDCR获取。

英文摘要:

This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions. We approximate the difference with models' generalization abilities so that it fits in the standard machine learning framework and can be efficiently computed. In contrast to the state-of-the-art approach, which relies on the learner's adaptation speed to new distribution, the proposed approach only requires evaluating the model's generalization ability. We provide a theoretical explanation for the advantage of the proposed method, and our experiments show that the proposed technique is 1.9--11.0$\times$ more sample efficient and 9.4--32.4 times quicker than the previous method on various tasks. The source code is available at \url{https://github.com/yuanpeng16/EDCR}.

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。

↑