Simplicial Convolutional Neural Networks
This work addresses the problem of processing higher-order relational data in networked systems for researchers in graph machine learning, representing an incremental extension of graph neural networks to simplices.
The authors tackled the limitation of existing graph neural networks, which only process data on nodes, by proposing a simplicial convolutional neural network (SCNN) to learn from data on simplices like edges and triangles, and demonstrated its performance in imputing citations on a coauthorship complex.
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.