Joint embedding of structure and features via graph convolutional networks

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 \emph{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.

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Fast unfolding of communities in large networks
• Community detection in graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• Link Prediction in Complex Networks: A Survey
• Spectral Networks and Locally Connected Networks on Graphs
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Modeling polypharmacy side effects with graph convolutional networks
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• The map equation
• Variational Graph Auto-Encoders
• Emergence of communities in weighted networks
• Socioeconomic correlations and stratification in social-communication networks
• Disentangling Disentanglement in Variational Autoencoders
• Multi-Task Graph Autoencoders
• Flexible Attributed Network Embedding

Cited by in corpus (5)

• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• Graph Neural Networks: Taxonomy, Advances and Trends
• AI-guided inverse design and discovery of recyclable vitrimeric polymers
• Computational Human Dynamics
• Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks