Can I read Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation on EtoBox?

Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation by Lu, Ping-En; Chang, Cheng-Shang is a scholarly article available to read on EtoBox.

What is Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation about?

The network embedding problem that maps nodes in a graph to vectors in Euclidean space can be very useful for addressing several important tasks on a graph. Recently, graph neural networks (GNNs) have been proposed for solving such a problem. However, most embedding algorithms and GNNs are difficult to interpret and do not scale well to handle millions of nodes. In this paper, we tackle the problem from a new perspective based on the equivalence of three constrained optimization problems: the network embedding problem, the trace maximization problem of the modularity matrix in a sampled graph, and the matrix factorization problem of the modularity matrix in a sampled graph. The optimal solutions to these three problems are the dominant eigenvectors of the modularity matrix. We proposed two algorithms that belong to a special class of graph convolutional networks (GCNs) for solving these problems: (i) Clustering As Feature Embedding GCN (CAFE-GCN) and (ii) sphere-GCN. Both algorithms are stable trace maximization algorithms, and they yield good approximations of dominant eigenvectors. Moreover, there are linear-time implementations for sparse graphs. In addition to solving the netwo

Author

Lu, Ping-En; Chang, Cheng-Shang

Published

2020

Language

EN