A Block-based Generative Model for Attributed Networks Embedding
Preprint
Abstract
Attributed network embedding has attracted plenty of interest in recent years. It aims to learn task-independent, low-dimensional, and continuous vectors for nodes preserving both topology and attribute information. Most of the existing methods, such as random-walk based methods and GCNs, mainly focus on the local information, i.e., the attributes of the neighbours. Thus, they have been well studied for assortative networks (i.e., networks with communities) but ignored disassortative networks (i.e., networks with multipartite, hubs, and hybrid structures), which are common in the real world. To enable model both assortative and disassortative networks, we propose a block-based generative model for attributed network embedding from a probability perspective. Specifically, the nodes are assigned to several blocks wherein the nodes in the same block share the similar linkage patterns. These patterns can define assortative networks containing communities or disassortative networks with the multipartite, hub, or any hybrid structures. To preserve the attribute information, we assume that each node has a hidden embedding related to its assigned block. We use a neural network to characterize the nonlinearity between node embeddings and node attributes. We perform extensive experiments on real-world and synthetic attributed networks. The results show that our proposed method consistently outperforms state-of-the-art embedding methods for both clustering and classification tasks, especially on disassortative networks.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Graph Attention Auto-Encoders2020
- How to predict social relationships — Physics-inspired approach to link predictionPhysica A: Statistical Mechanics and its Applications, 2019
- Change point detection in social networks—Critical review with experimentsComputer Science Review, 2018
- Attributed Social Network EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2018
- Stochastic Blockmodeling and Variational Bayes Learning for Signed Network AnalysisIEEE Transactions on Knowledge and Data Engineering, 2017
- Structure and inference in annotated networksNature Communications, 2016
- Stochastic block model and exploratory analysis in signed networksPhysical Review E, 2015
- Detecting communities and their evolutions in dynamic social networks—a Bayesian approachMachine Learning, 2010
- Missing and spurious interactions and the reconstruction of complex networksProceedings of the National Academy of Sciences of the United States of America, 2009
- Stochastic blockmodels: First stepsSocial Networks, 1983