GEMSEC: Graph Embedding with Self Clustering

Abstract

Modern graph embedding procedures can efficiently process graphs with millions of nodes. In this paper, we propose GEMSEC -- a graph embedding algorithm which learns a clustering of the nodes simultaneously with computing their embedding. GEMSEC is a general extension of earlier work in the domain of sequence-based graph embedding. GEMSEC places nodes in an abstract feature space where the vertex features minimize the negative log-likelihood of preserving sampled vertex neighborhoods, and it incorporates known social network properties through a machine learning regularization. We present two new social network datasets and show that by simultaneously considering the embedding and clustering problems with respect to social properties, GEMSEC extracts high-quality clusters competitive with or superior to other community detection algorithms. In experiments, the method is found to be computationally efficient and robust to the choice of hyperparameters.

References in corpus (9)

• Efficient Estimation of Word Representations in Vector Space
• Community detection in graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• Cooperative Game Theory Approaches for Network Partitioning
• Inductive Representation Learning on Large Graphs
• Structure and tie strengths in mobile communication networks
• Graph Embedding Techniques, Applications, and Performance: A Survey
• struc2vec: Learning Node Representations from Structural Identity
• subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs

Cited by in corpus (15)

• Predicting the speed of epidemics spreading on networks
• What Do Your Friends Think? Efficient Polling Methods for Networks Using Friendship Paradox
• vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
• Network Shuffling: Privacy Amplification via Random Walks
• Minimum Long-Loop Feedback Vertex Set and Network Dismantling
• Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification
• Multiple Kernel Representation Learning on Networks
• Topic-aware latent models for representation learning on networks
• SPECTRE: Seedless Network Alignment via Spectral Centralities
• Large-scale multi-objective influence maximisation with network downscaling
• Beyond the Coverage of Information Spreading: Analytical and Empirical Evidence of Re-exposure in Large-scale Online Social Networks
• Balanced Order Batching with Task-Oriented Graph Clustering
• Transfer Learning for Node Regression Applied to Spreading Prediction
• Generative Temporal Link Prediction via Self-tokenized Sequence Modeling
• Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks