Using Graph Convolutional Networks to Compute Approximations of Dominant Eigenvectors
| Autor: | Ping-En Lu, Cheng-Shang Chang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Discrete mathematics
Computer Networks and Communications Approximations of π Euclidean space Computer science 020206 networking & telecommunications 010103 numerical & computational mathematics 02 engineering and technology Special class 01 natural sciences Graph Hardware and Architecture 0202 electrical engineering electronic engineering information engineering Graph (abstract data type) Symmetric matrix 0101 mathematics Software Eigenvalues and eigenvectors |
| Zdroj: | ACM SIGMETRICS Performance Evaluation Review. 48:3-5 |
| ISSN: | 0163-5999 |
| DOI: | 10.1145/3439602.3439605 |
| Popis: | Graph Convolutional Networks (GCN) have been very popular for the network embedding problem that maps nodes in a graph to vectors in a Euclidean space. In this short paper, we show that a special class of GCNs compute approximations of dominant eigenvectors of symmetric matrices with zero column sums. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|