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 2110.02585cs.LGeess.SP
收藏

简单卷积神经网络

Simplicial Convolutional Neural Networks

Delft University of Technology(代尔夫特理工大学)

Maosheng Yang, Elvin Isufi, Geert Leus

摘要:

图可以通过将网络数据表示为节点并将其成对关系表示为边来对网络数据进行建模。最近,信号处理和神经网络已经被扩展到处理和学习图上的数据,在诸如图信号重构、图或节点分类以及链接预测的任务中取得了成就。然而,这些方法仅适用于定义在图的节点上的数据。在本文中,我们提出了一个单纯卷积神经网络(SCNN)架构,从定义在单纯形上的数据中学习,例如,节点,边,三角形等。我们研究了SCNN的排列和方向的等方差,复杂性和频谱分析。最后,我们测试了SCNN的性能归咎于引文的合著复杂。

英文摘要:

Graphs can model networked data by representing them as nodes and their pairwise relationships as edges. Recently, signal processing and neural networks have been extended to process and learn from data on graphs, with achievements in tasks like graph signal reconstruction, graph or node classifications, and link prediction. However, these methods are only suitable for data defined on the nodes of a graph. In this paper, we propose a simplicial convolutional neural network (SCNN) architecture to learn from data defined on simplices, e.g., nodes, edges, triangles, etc. We study the SCNN permutation and orientation equivariance, complexity, and spectral analysis. Finally, we test the SCNN performance for imputing citations on a coauthorship complex.

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。

↑