arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.07299cs.LGcs.AIstat.ML
收藏

图序列的自回归模型

Autoregressive Models for Sequences of Graphs

Università della Svizzera italiana(瑞士意大利语大学);University of Manitoba(曼尼托巴大学);University of Exeter(埃克塞特大学);Politecnico di Milano(米兰理工大学)

Daniele Zambon, Daniele Grattarola, Lorenzo Livi, Cesare Alippi

摘要:

本文提出了一种图序列的自回归(AR)模型,它推广了传统的AR模型。第一个新颖之处在于形式化的AR模型的一个非常一般的家庭的图形,其特征在于一个可变的拓扑结构,和属性与节点和边缘。一个图神经网络(GNN)也被提出来学习与图生成过程(GGP)相关联的AR函数,并随后预测序列中的下一个图。所提出的方法进行了比较与合成GGP的四个基线,表示一个显着更好的性能在所有考虑的问题。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑