Implementation of SCORE, SCORE+ and Mixed-SCORE

Implementation of community detection algorithm SCORE in the paper J. Jin (2015) , and SCORE+ in J. Jin, Z. Ke and S. Luo (2018) . Membership estimation algorithm called Mixed-SCORE in J. Jin, Z. Ke and S. Luo (2017) .

R and C/C++ Wrappers to Run the Leiden find_partition() Function

An R to C/C++ interface that runs the Leiden community detection algorithm to find a basic partition (). It runs the equivalent of the 'leidenalg' find_partition() function, which is given in the 'leidenalg' distribution file 'leiden/src/functions.py'. This package includes the required source code files from the official 'leidenalg' distribution and functions from the R 'igraph' package. The 'leidenalg' distribution is available from < https://github.com/vtraag/leidenalg/> and the R 'igraph' package is available from < https://igraph.org/r/>. The Leiden algorithm is described in the article by Traag et al. (2019) . Leidenbase includes code from the packages: igraph version 0.9.8 with license GPL (>= 2), leidenalg version 0.8.10 with license GPL 3.

Detecting Spatial Clustering Based on Connection Cost Between Grids

Based on landscape connectivity, spatial boundaries were identified using community detection algorithm at grid level. Methods using raster as input and the value of each cell of the raster is the "smoothness" to indicate how easy the cell connecting with neighbor cells. Details about the 'habCluster' package methods can be found in Zhang et al. .

Semidefinite Programming for Fitting Block Models of Equal Block Sizes

An ADMM implementation of SDP-1, a semidefinite programming relaxation of the maximum likelihood estimator for fitting a block model. SDP-1 has a tendency to produce equal-sized blocks and is ideal for producing a form of network histogram approximating a nonparametric graphon model. Alternatively, it can be used for community detection. (This is experimental code, proceed with caution.)

Automatic Knowledge Classification

A tidy framework for automatic knowledge classification and visualization. Currently, the core functionality of the framework is mainly supported by modularity-based clustering (community detection) in keyword co-occurrence network, and focuses on co-word analysis of bibliometric research. However, the designed functions in 'akc' are general, and could be extended to solve other tasks in text mining as well.

Consistent Estimation of the Number of Communities via Regularized Network Embedding

The network analysis plays an important role in numerous application domains including biomedicine. Estimation of the number of communities is a fundamental and critical issue in network analysis. Most existing studies assume that the number of communities is known a priori, or lack of rigorous theoretical guarantee on the estimation consistency. This method proposes a regularized network embedding model to simultaneously estimate the community structure and the number of communities in a unified formulation. The proposed model equips network embedding with a novel composite regularization term, which pushes the embedding vector towards its center and collapses similar community centers with each other. A rigorous theoretical analysis is conducted, establishing asymptotic consistency in terms of community detection and estimation of the number of communities. Reference: Ren, M., Zhang S. and Wang J. (2022). "Consistent Estimation of the Number of Communities via Regularized Network Embedding". Biometrics, .

Community Ecology Package

Ordination methods, diversity analysis and other functions for community and vegetation ecologists.

Fast and Robust Multi-Scale Graph Clustering

A graph community detection algorithm that aims to be performant on large graphs and robust, returning consistent results across runs. SpeakEasy 2 (SE2), the underlying algorithm, is described in Chris Gaiteri, David R. Connell & Faraz A. Sultan et al. (2023) . The core algorithm is written in 'C', providing speed and keeping the memory requirements low. This implementation can take advantage of multiple computing cores without increasing memory usage. SE2 can detect community structure across scales, making it a good choice for biological data, which often has hierarchical structure. Graphs can be passed to the algorithm as adjacency matrices using base 'R' matrices, the 'Matrix' library, 'igraph' graphs, or any data that can be coerced into a matrix.

Just Another Latent Space Network Clustering Algorithm

Fit latent space network cluster models using an expectation-maximization algorithm. Enables flexible modeling of unweighted or weighted network data (with or without noise edges), supporting both directed and undirected networks (with or without degree and strength heterogeneity). Designed to handle large networks efficiently, it allows users to explore network structure through latent space representations, identify clusters (i.e., community detection) within network data, and simulate networks with varying clustering, connectivity patterns, and noise edges. Methodology for the implementation is described in Arakkal and Sewell (2025) .

Tracking Communities in Changing Temporal Networks

Tools for temporal networks that change over time, where nodes enter and leave, groups form, split, merge and dissolve, and periods differ in size. The temporal fitters track nodes and communities across periods. A community keeps one identifier while it persists, and a newly formed group receives a new one. Two-stage fitters run Louvain or Leiden community detection in each period and link communities in linked periods by Jaccard similarity, the overlap coefficient or node-strength weighted variants. The 'layer_links' argument sets which periods are directly linked, adjacent periods only by default. By default all periods are fitted jointly, so later periods can change earlier labels, and tracking = 'filtered' prevents this. Multislice modularity (Mucha et al. 2010) and Hungarian matching are included as comparison methods, and a bootstrap stability score helps choose between the two-stage and multislice approaches.