Abstract
Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and node clustering. However, a fundamental flaw exists in Variational Autoencoder (VAE)-based approaches. Specifically, merely minimizing the loss of VAE increases the deviation from its primary objective. Focusing on Variational Graph Autoencoder for Community Detection (VGAECD) we found that optimizing the loss using the stochastic gradient descent often leads to sub-optimal community structure especially when initialized poorly. We address this shortcoming by introducing a dual optimization procedure. This procedure aims to guide the optimization process and encourage learning of the primary objective. Additionally, we linearize the encoder to reduce the number of learning parameters. The outcome is a robust algorithm that outperforms its predecessor.
Highlights
IntroductionNetworks (graphs) with nodes (vertices) and edges (links) are a considerable simplification of complex patterns observed in real life, permitting studies of complex systems
Networks with nodes and edges are a considerable simplification of complex patterns observed in real life, permitting studies of complex systems
We focus our attention on a variant of VGAE, namely Variational Graph Autoencoder for Community Detection (VGAECD) [22]
Summary
Networks (graphs) with nodes (vertices) and edges (links) are a considerable simplification of complex patterns observed in real life, permitting studies of complex systems. Researchers who published together can be related in a collaboration network [2] Movies and their respective critics can be presented as a bipartite graph with the edge-weight indicating a user-movie rating [3] which further allow applications like recommender systems [4]. A recovered community structure with high modularity implies good partitioning. To this date, community detection algorithms have evolved from traditional algorithms to the usage of complex learning algorithms like graph representation learning [9,10]. Graph representation learning is extremely appealing because it provides a generalized application for downstream tasks such as link prediction [11], classification [12] and clustering [13]. By exploiting existing literature on representation learning, these tasks can be solved by reusing existing machine learning techniques
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
