Autoregressive Models for Sequences of Graphs
Machine Learning
2019-03-19 v1 Artificial Intelligence
Machine Learning
Abstract
This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models. A first novelty consists in formalising the AR model for a very general family of graphs, characterised by a variable topology, and attributes associated with nodes and edges. A graph neural network (GNN) is also proposed to learn the AR function associated with the graph-generating process (GGP), and subsequently predict the next graph in a sequence. The proposed method is compared with four baselines on synthetic GGPs, denoting a significantly better performance on all considered problems.
Cite
@article{arxiv.1903.07299,
title = {Autoregressive Models for Sequences of Graphs},
author = {Daniele Zambon and Daniele Grattarola and Lorenzo Livi and Cesare Alippi},
journal= {arXiv preprint arXiv:1903.07299},
year = {2019}
}
Comments
International Joint Conference on Neural Networks (IJCNN) 2019