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 1806.08829cs.LGstat.ML
收藏

图的扩散散射变换

Diffusion Scattering Transforms on Graphs

University of Pennsylvania(宾夕法尼亚大学);Courant Institute of Mathematical Sciences(库朗数学科学研究所);New York University(纽约大学)

Fernando Gama, Alejandro Ribeiro, Joan Bruna

摘要:

稳定性是数据分析的一个关键方面。在许多应用中,稳定性的自然概念是几何的,例如在计算机视觉中所示。散射变换构造深度卷积表示,这些表示被证明对输入变形是稳定的。这种对变形的稳定性可以解释为相对于域的度量结构的变化的稳定性。在这项工作中,我们表明,散射变换可以推广到非欧几里德域使用扩散小波,同时保持一个概念的稳定性相对于度量变化的域,测量扩散映射。所得到的表示对于域的度量扰动是稳定的,同时能够捕获“高频”信息,类似于欧几里得散射。

英文摘要:

Stability is a key aspect of data analysis. In many applications, the natural notion of stability is geometric, as illustrated for example in computer vision. Scattering transforms construct deep convolutional representations which are certified stable to input deformations. This stability to deformations can be interpreted as stability with respect to changes in the metric structure of the domain. In this work, we show that scattering transforms can be generalized to non-Euclidean domains using diffusion wavelets, while preserving a notion of stability with respect to metric changes in the domain, measured with diffusion maps. The resulting representation is stable to metric perturbations of the domain while being able to capture "high-frequency" information, akin to the Euclidean Scattering.

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。

↑