使多轴模型对乘性噪声具有鲁棒性:如何,为何?
Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?
AI总结:
本文提出MED-MAGMA算法,用于拟合受乘性噪声干扰的多轴模型,通过在单细胞RNA测序等领域的公开数据集验证,证明其能学习具有更好局部和全局结构的网络。
摘要:
在本文中,我们开发了一种图学习算法MED-MAGMA,用于拟合受乘性噪声干扰的多轴(Kronecker-sum-结构)模型。这种类型的噪声在许多应用领域中是自然存在的,例如单细胞RNA测序,在其中它自然捕捉了RNA测序平台的技术偏差。我们的工作在Single Cell Expression Atlas中的每个公开数据集上都与先前的工作进行了评估,证明了我们的方法能够学习具有更好局部和全局结构的网络。MED-MAGMA作为Python包(MED-MAGMA)提供。
英文摘要:
In this paper we develop a graph-learning algorithm, MED-MAGMA, to fit multi-axis (Kronecker-sum-structured) models corrupted by multiplicative noise. This type of noise is natural in many application domains, such as that of single-cell RNA sequencing, in which it naturally captures technical biases of RNA sequencing platforms. Our work is evaluated against prior work on each and every public dataset in the Single Cell Expression Atlas under a certain size, demonstrating that our methodology learns networks with better local and global structure. MED-MAGMA is made available as a Python package (MED-MAGMA).
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。