Probabilistic Learning on Graphs via Contextual Architectures

Federico Errica
Federico Errica

JOURNAL OF MACHINE LEARNING RESEARCH, pp. 1-39, 2020.

Cited by: 0|Views3

Abstract:

We propose a novel methodology for representation learning on graph-structured data, in which a stack of Bayesian Networks learns different distributions of a vertex's neighbourhood. Through an incremental construction policy and layer-wise training, we can build deeper architectures with respect to typical graph convolutional neural netw...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments