Loading...
Joint embedding of structure and features via graph convolutional networks
Title / Series / Name
Applied Network Science
Publication Volume
5
Publication Issue
1
Pages
Editors
Keywords
Attributed networks
Autoencoders
Convolutional networks
Feature-network dependency
Graph
Network embedding
Multidisciplinary
Computer Networks and Communications
Computational Mathematics
Autoencoders
Convolutional networks
Feature-network dependency
Graph
Network embedding
Multidisciplinary
Computer Networks and Communications
Computational Mathematics
URI
https://hdl.handle.net/20.500.14018/28395
Abstract
The creation of social ties is largely determined by the entangled effects of people’s similarities in terms of individual characters and friends. However, feature and structural characters of people usually appear to be correlated, making it difficult to determine which has greater responsibility in the formation of the emergent network structure. We propose AN2VEC, a node embedding method which ultimately aims at disentangling the information shared by the structure of a network and the features of its nodes. Building on the recent developments of Graph Convolutional Networks (GCN), we develop a multitask GCN Variational Autoencoder where different dimensions of the generated embeddings can be dedicated to encoding feature information, network structure, and shared feature-network information. We explore the interaction between these disentangled characters by comparing the embedding reconstruction performance to a baseline case where no shared information is extracted. We use synthetic datasets with different levels of interdependency between feature and network characters and show (i) that shallow embeddings relying on shared information perform better than the corresponding reference with unshared information, (ii) that this performance gap increases with the correlation between network and feature structure, and (iii) that our embedding is able to capture joint information of structure and features. Our method can be relevant for the analysis and prediction of any featured network structure ranging from online social systems to network medicine.
Topic
Publisher
Place of Publication
Type
Journal article
Date
2020-12-01
Language
ISBN
Identifiers
10.1007/s41109-019-0237-x