20 Years of Network Community Detection

  title={20 Years of Network Community Detection},
  author={Santo Fortunato and Mark E. J. Newman},
A fundamental technical challenge in the analysis of network data is the automated discovery of communities — groups of nodes that are strongly connected or that share similar features or roles. In this commentary we review progress in the field over the last 20 years. 

Local dominance unveils clusters in networks

This work considers another perspective built on the notion of local dominance, where low-degree nodes are assigned to the basin of influence of high- degree nodes, and design an efficient algorithm based on local information.

Finding community structure using the ordered random graph model

This study proposes an ordering algorithm based on the maximum-likelihood estimate of the ordered random graph model and shows that the proposed method allows us to more clearly identify community structures than the existing ordering algorithms.

Automatic detection of multilevel communities: scalable and resolution-limit-free

This paper proposes a strict definition for the term “plateau,” which has been always loosely used in previous literature, to help remove random and irrelevant outputs automatically —without any artificial selection, and has “neat” outputs that include only stable and informative plateaus.

The Bayan Algorithm: Detecting Communities in Networks Through Exact and Approximate Optimization of Modularity

This work proposes the Bayan algorithm, a branch-and-cut scheme that solves a sparse integer programming formulation of the modularity maximization problem to optimality or approximate it within a factor, and analyzes the performance of Bayan against 22 existing algorithms.

Implicit models, latent compression, intrinsic biases, and cheap lunches in community detection

The results undermine the implications of the “no free lunch” theorem for community detection, both conceptually and in practice, since it is confined to unstructured data instances, unlike relevant community detection problems which are structured by requirement.

A Useful Criterion on Studying Consistent Estimation in Community Detection

Numerical results for computer-generated networks support the finding that spectral methods considered in this paper achieve the threshold of separation condition.

Dimension matters when modeling network communities in hyperbolic spaces

It is shown that there is an important qualitativeerence between the lowest-dimensional model and its higher-dimensional counterparts with respect to how similarity between nodes restricts connection probabilities, and considering only one more dimension allows for more realistic and diverse community structures.

Bipartite Mixed Membership Distribution-Free Model. A novel model for community detection in overlapping bipartite weighted networks

A novel model, the Bipartite Mixed Membership Distribution-Free (BiMMDF) model, which enjoys its advantage by allowing all elements of an adjacency matrix to be generated from any distribution as long as the expectation adjacencies has a block structure related to node memberships under BiMMDF.

Trading off Quality for Efficiency of Community Detection: An Inductive Method across Graphs

This work proposes an alternative inductive community detection (ICD) method across graphs of a system or scenario to alleviate the NP-hard challenge and demonstrates that ICD can achieve a significant trade-off between quality and efficiency over various baselines.



Generalized communities in networks

A principled method for detecting generalized structure in empirical network data is described and it is demonstrated with real-world examples how it can be used to learn new things about the shape and meaning of networks.

Comparing community structure identification

It is found that the most accurate methods tend to be more computationally expensive, and that both aspects need to be considered when choosing a method for practical purposes.

Fast unfolding of communities in large networks

This work proposes a heuristic method that is shown to outperform all other known community detection methods in terms of computation time and the quality of the communities detected is very good, as measured by the so-called modularity.

Community detection in networks: Structural communities versus ground truth

It is shown that traditional community detection methods fail to find the metadata groups in many large networks, and that either the current modeling of community structure has to be substantially modified, or that metadata groups may not be recoverable from topology alone.

Fast algorithm for detecting community structure in networks.

  • M. Newman
  • Computer Science
    Physical review. E, Statistical, nonlinear, and soft matter physics
  • 2004
An algorithm is described which gives excellent results when tested on both computer-generated and real-world networks and is much faster, typically thousands of times faster, than previous algorithms.

Finding and evaluating community structure in networks.

  • M. NewmanM. Girvan
  • Computer Science
    Physical review. E, Statistical, nonlinear, and soft matter physics
  • 2004
It is demonstrated that the algorithms proposed are highly effective at discovering community structure in both computer-generated and real-world network data, and can be used to shed light on the sometimes dauntingly complex structure of networked systems.

Community detection in graphs

Community structure in social and biological networks

  • M. GirvanM. Newman
  • Computer Science
    Proceedings of the National Academy of Sciences of the United States of America
  • 2002
This article proposes a method for detecting communities, built around the idea of using centrality indices to find community boundaries, and tests it on computer-generated and real-world graphs whose community structure is already known and finds that the method detects this known structure with high sensitivity and reliability.

Structure and inference in annotated networks

This work focuses in particular on the problem of community detection in networks and develops a mathematically principled approach that combines a network and its metadata to detect communities more accurately than can be done with either alone.

Finding Statistically Significant Communities in Networks

OSLOM (Order Statistics Local Optimization Method), the first method capable to detect clusters in networks accounting for edge directions, edge weights, overlapping communities, hierarchies and community dynamics, is presented.