Community Detection in Networks with Node Attributes

Abstract

Community detection algorithms are fundamental tools that allow us to uncover organizational principles in networks. When detecting communities, there are two possible sources of information one can use: the network structure, and the features and attributes of nodes. Even though communities form around nodes that have common edges and common attributes, typically, algorithms have only focused on one of these two data modalities: community detection algorithms traditionally focus only on the network structure, while clustering algorithms mostly consider only node attributes. In this paper, we develop Communities from Edge Structure and Node Attributes (CESNA), an accurate and scalable algorithm for detecting overlapping communities in networks with node attributes. CESNA statistically models the interaction between the network structure and the node attributes, which leads to more accurate community detection as well as improved robustness in the presence of noise in the network structure. CESNA has a linear runtime in the network size and is able to process networks an order of magnitude larger than comparable approaches. Last, CESNA also helps with the interpretation of detected communities by finding relevant node attributes for each community.

Published in the proceedings of IEEE ICDM '13

Cited by in corpus (36)

• Structure and inference in annotated networks
• A Comprehensive Survey on Community Detection with Deep Learning
• Community detection in node-attributed social networks: a survey
• Diversity of meso-scale architecture in human and non-human connectomes
• Covariate-assisted spectral clustering
• Exposing Fake Images with Forensic Similarity Graphs
• Community detection with node attributes in multilayer networks
• Community Detection with Side Information: Exact Recovery under the Stochastic Block Model
• CLARE: A Semi-supervised Community Detection Algorithm
• Integrating Prior Knowledge in Mixed Initiative Social Network Clustering
• PANE: scalable and effective attributed network embedding
• Community Detection and Improved Detectability in Multiplex Networks
• Effective and Scalable Clustering on Massive Attributed Graphs
• Spectral Clustering of Attributed Multi-relational Graphs
• Latent Space Model for Multi-Modal Social Data
• Detection of Community Structures in Networks with Nodal Features based on Generative Probabilistic Approach
• Relational Thematic Clustering with Mutually Preferred Neighbors
• Social Network Mediation Analysis: a Latent Space Approach
• Publishing Community-Preserving Attributed Social Graphs with a Differential Privacy Guarantee
• MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs
• Efficiently Clustering Very Large Attributed Graphs
• Mapping flows on weighted and directed networks with incomplete observations
• A Method for Characterizing Communities in Dynamic Attributed Complex Networks
• Clustering and Community Detection with Imbalanced Clusters
• Interpreting communities based on the evolution of a dynamic attributed network
• Analysis of multiview legislative networks with structured matrix factorization: Does Twitter influence translate to the real world?
• Deep Graph Clustering via Mutual Information Maximization and Mixture Model
• Detecting Localized Categorical Attributes on Graphs
• Simulating systematic bias in attributed social networks and its effect on rankings of minority nodes
• Community Structure Characterization
• A Versatile Framework for Attributed Network Clustering via K-Nearest Neighbor Augmentation
• A Local Perspective-based Model for Overlapping Community Detection
• Measuring Proximity in Attributed Networks for Community Detection
• Community Detection Algorithm Combining Stochastic Block Model and Attribute Data Clustering
• Learning Optimal Graph Filters for Clustering of Attributed Graphs
• Quantifying metadata relevance to network block structure using description length