A Monte Carlo evaluation of weighted community detection algorithms
Open accessAbstract
The past decade has been marked with a proliferation of community detection algorithms that aim to organize nodes (e.g., individuals, brain regions, variables) into modular structures that indicate subgroups, clusters, or communities. Motivated by the emergence of big data across many fields of inquiry, these methodological developments have primarily focused on the detection of communities of nodes from matrices that are very large. However, it remains unknown if the algorithms can reliably detect communities in smaller graph sizes (i.e., 1000 nodes and fewer) which are commonly used in brain research. More importantly, these algorithms have predominantly been tested only on binary or sparse count matrices and it remains unclear the degree to which the algorithms can recover community structure for different types of matrices, such as the often used cross-correlation matrices representing functional connectivity across predefined brain regions. Of the publicly available approaches for weighted graphs that can detect communities in graph sizes of at least 1000, prior research has demonstrated that Newman's spectral approach (i.e., Leading Eigenvalue), Walktrap, Fast Modularity, the Louvain method (i.e., multilevel community method), Label Propagation, and Infomap all recover communities exceptionally well in certain circumstances. The purpose of the present Monte Carlo simulation study is to test these methods across a large number of conditions, including varied graph sizes and types of matrix (sparse count, correlation, and reflected Euclidean distance), to identify which algorithm is optimal for specific types of data matrices. The results indicate that when the data are in the form of sparse count networks (such as those seen in diffusion tensor imaging), Label Propagation and Walktrap surfaced as the most reliable methods for community detection. For dense, weighted networks such as correlation matrices capturing functional connectivity, Walktrap consistently outperformed the other approaches for recovering communities.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Different community detection algorithms can provide unique results and not all are appropriate for any given experimental condition.
“different community detection algorithms can provide unique results and all are not appropriate for any given experimental condition (Gates et al., 2016).”
From Development of large-scale functional networks from birth to adulthood: A guide to the neuroimaging literature (2017) · cites this paper as Gates et al., 2016
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Collective dynamics of ‘small-world’ networks
Watts, D. J., & Strogatz, S. H. (1998) · Nature · doi:10.1038/30918 · Cited by 43,060 · cited 1× · see citing works
“…been used to examine the organization of networks across disparate research foci, including the World Wide Web (Latora and Marchiori, 2001), social networks (Zachary, 1977), the power grid (Watts and Strogatz, 1998), brain processes (Bassett and Bullmore, 2006), and food-webs (Dunne et al., 2002).”
BackgroundFast unfolding of communities in large networks
Blondel, V. D., Guillaume, J.-L., Lambiotte, R., & Lefebvre, E. (2008) · Journal of Statistical Mechanics: Theory and Experiment · doi:10.1088/1742-5468/2008/10/p10008 · Cited by 21,424 · cited 22× · see citing works
“The most popular algorithms have predominantly been evaluated using empirical data (Clauset et al., 2004; Newman, 2006; Blondel et al., 2008).”
BackgroundMethodInfluentialHierarchical Grouping to Optimize an Objective Function
Ward, J. H. (1963) · Journal of the American Statistical Association · doi:10.1080/01621459.1963.10500845 · Cited by 21,341 · cited 1× · see citing works
“A traditional hierarchical clustering technique (Ward’s method; Ward, 1963) is then applied to this distance matrix, forming communities by minimizing the sum of squared distances of each node to the other nodes within its own community.”
MethodStatistical mechanics of complex networks
Albert, R., & Barabási, A.-L. (2002) · Reviews of Modern Physics · doi:10.1103/revmodphys.74.47 · Cited by 20,471 · cited 1× · see citing works
“The presence of large-scale data collection, greater computing power, and a desire to understand behaviors of systems as a whole has altered the way in which networks are approached (Albert and Barabási, 2002).”
BackgroundCommunity structure in social and biological networks
Girvan, M., & Newman, M. E. J. (2002) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.122653799 · Cited by 15,502 · cited 2× · see citing works
“The first index is the commonly used Girvan and Newman (2002)’s approach of looking at the fraction of correctly classified nodes.”
MethodFinding and evaluating community structure in networks
Newman, M. E. J., & Girvan, M. (2004) · Physical Review E · doi:10.1103/physreve.69.026113 · Cited by 13,931 · cited 1× · see citing works
“When the strength of edges within a group is larger than what is expected at random, modularity rises (Newman and Girvan, 2003; Newman, 2004a).”
BackgroundModularity and community structure in networks
Newman, M. E. J. (2006) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0601602103 · Cited by 12,256 · cited 19× · see citing works
“Walktrap outperformed the other methods in terms of average ARI HA across all conditions, with effect sizes for the differences between Walktrap and other methods ranging from small ( d = 0.14 for Label Propagation) to large ( d > 1.30 for Fast modularity and NSA; see Supplemental Table 10).”
BackgroundMethodResultInfluentialComplex network measures of brain connectivity: Uses and interpretations
Rubinov, M., & Sporns, O. (2010) · NeuroImage · doi:10.1016/j.neuroimage.2009.10.003 · Cited by 11,522 · cited 1× · see citing works
“…evident in neuroimaging studies where community detection is used on functional connectivity correlation matrices obtained from fMRI data (e.g., Mumford et al., 2010; Rubinov and Sporns, 2010) as well as on matrices generated from diffusion tensor imaging (DTI; e.g., Bassett et al., 2011).”
MethodFortunato, S. (2010) · Physics Reports · doi:10.1016/j.physrep.2009.11.002 · Cited by 11,293 · cited 7× · see citing works
“This algorithm also uses the definition that there should be minimal transitions of a random walker between clusters and more transitions within clusters (Fortunato, 2010).”
BackgroundMethodInfluentialHubert, L., & Arabie, P. (1985) · Journal of Classification · doi:10.1007/bf01908075 · Cited by 8,219 · see citing works
Power-Law Distributions in Empirical Data
Clauset, A., Shalizi, C. R., & Newman, M. E. J. (2009) · SIAM Review · doi:10.1137/070710111 · Cited by 8,019 · cited 2× · see citing works
“Power law distribution appropriately describes data that has a long tail containing rare but extreme values (Clauset et al., 2009) and has become a guiding property in the generation and testing of algorithms (Newman, 2006; Barabási, 2013).”
BackgroundFinding community structure in very large networks
Clauset, A., Newman, M. E. J., & Moore, C. (2004) · Physical Review E · doi:10.1103/physreve.70.066111 · Cited by 7,390 · cited 2× · see citing works
“Fast modularity scales up the ability of a previous greedy algorithm (Newman, 2004b) for use on matrices as large as 10 million (Clauset et al., 2004).”
MethodPower-law distributions in empirical data
Clauset, A. J., Shalizi, C. R., & Newman, M. E. J. (2018) · Figshare · doi:10.1184/r1/6586835.v1 · Cited by 6,736 · see citing works
Fast algorithm for detecting community structure in networks
Newman, M. E. J. (2004) · Physical Review E · doi:10.1103/physreve.69.066133 · Cited by 5,415 · cited 2× · see citing works
“Fast modularity scales up the ability of a previous greedy algorithm (Newman, 2004b) for use on matrices as large as 10 million (Clauset et al., 2004).”
BackgroundMethodEfficient behavior of small-world networks
Latora, V., & Marchiori, M. (2001) · Physical Review Letters · doi:10.1103/physrevlett.87.198701 · Cited by 5,119 · cited 2× · see citing works
“Network theory has been used to examine the organization of networks across disparate research foci, including the World Wide Web (Latora and Marchiori, 2001), social networks (Zachary, 1977), the power grid (Watts and Strogatz, 1998), brain processes (Bassett and Bullmore, 2006), and food-webs…”
MethodAn Information Flow Model for Conflict and Fission in Small Groups
Zachary, W. W. (1977) · Journal of Anthropological Research · doi:10.1086/jar.33.4.3629752 · Cited by 4,709 · cited 1× · see citing works
“…been used to examine the organization of networks across disparate research foci, including the World Wide Web (Latora and Marchiori, 2001), social networks (Zachary, 1977), the power grid (Watts and Strogatz, 1998), brain processes (Bassett and Bullmore, 2006), and food-webs (Dunne et al., 2002).”
BackgroundMaps of random walks on complex networks reveal community structure
Rosvall, M., & Bergstrom, C. T. (2008) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0706851105 · Cited by 4,583 · see citing works
The structure of scientific collaboration networks
Newman, M. E. J. (2001) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.98.2.404 · Cited by 4,550 · cited 1× · see citing works
“This distribution has long been considered an aspect inherent in many networks containing counts, from large networks such as the world wide web (Albert et al., 1999) to biological systems (Clauset et al., 2009) to smaller networks of scientific collaborators (Newman, 2001).”
BackgroundDiameter of the World-Wide Web
Albert, R., Jeong, H., & Barabási, A.-Ĺ. (1999) · Nature · doi:10.1038/43601 · Cited by 4,240 · cited 1× · see citing works
“This distribution has long been considered an aspect inherent in many networks containing counts, from large networks such as the world wide web (Albert et al., 1999) to biological systems (Clauset et al., 2009) to smaller networks of scientific collaborators (Newman, 2001).”
BackgroundFunctional Network Organization of the Human Brain
Power, J. D., Cohen, A. L., Nelson, S. M., Wig, G. S., Barnes, K. A., Church, J. A., Vogel, A. C., Laumann, T. O., Miezin, F. M., Schlaggar, B. L., et al. (2011) · Neuron · doi:10.1016/j.neuron.2011.09.006 · Cited by 4,124 · cited 1× · see citing works
“Given the exceptional performance on large graphs (on the order of thousands), neuroimagers routinely apply community detection algorithms to graphs with node size on the order of hundreds (e.g., Power et al., 2011) and smaller (e.g., He et al., 2009).”
MethodNear linear time algorithm to detect community structures in large-scale networks
Raghavan, U. N., Albert, R., & Kumara, S. R. T. (2007) · Physical Review E · doi:10.1103/physreve.76.036106 · Cited by 3,535 · cited 2× · see citing works
“For sparse count matrices (such as those used for structural brain connections), Label Propagation (Raghavan et al., 2007), and Walktrap perform equally well under varied conditions.”
BackgroundMethodBenchmark graphs for testing community detection algorithms
Lancichinetti, A., Fortunato, S., & Radicchi, F. (2008) · Physical Review E · doi:10.1103/physreve.78.046110 · Cited by 3,058 · cited 2× · see citing works
“The first data generation algorithm is the publicly available Lancichinetti-Fortunato (LFR) benchmark approach for arriving at sparse count matrices (Lancichinetti et al., 2008).”
MethodResolution limit in community detection
Fortunato, S., & Barthélemy, M. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0605965104 · Cited by 3,024 · cited 2× · see citing works
“…of communities (Danon et al., 2006); however, it comes with limitations such as a reported inability to recover graphs with small communities (Fortunato and Barthélemy, 2007; Porter et al., 2009), different sized communities (Pons and Latapy, 2006), and sometimes inflated modularity for…”
BackgroundBassett, D. S., & Bullmore, E. (2006) · The Neuroscientist · doi:10.1177/1073858406293182 · Cited by 2,600 · cited 2× · see citing works
“…been used to examine the organization of networks across disparate research foci, including the World Wide Web (Latora and Marchiori, 2001), social networks (Zachary, 1977), the power grid (Watts and Strogatz, 1998), brain processes (Bassett and Bullmore, 2006), and food-webs (Dunne et al., 2002).”
BackgroundDefining and identifying communities in networks
Radicchi, F., Castellano, C., Cecconi, F., Loreto, V., & Parisi, D. (2004) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0400054101 · Cited by 2,450 · cited 1× · see citing works
“When simulating the data we followed what Radicchi et al. (2004) define as a community in a strong sense.”
MethodDetecting community structure in networks
Newman, M. E. J. (2004) · The European Physical Journal B · doi:10.1140/epjb/e2004-00124-y · Cited by 2,031 · cited 2× · see citing works
“Fast modularity scales up the ability of a previous greedy algorithm (Newman, 2004b) for use on matrices as large as 10 million (Clauset et al., 2004).”
BackgroundMethodGuimerà, R., Mossa, S., Turtschi, A., & Amaral, L. A. N. (2005) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0407994102 · Cited by 1,772 · cited 1× · see citing works
“Communities are formally considered to be subgroups of nodes comprising a modular component that, in terms of edges, has higher within-community connectivity than expected by chance given the properties of the network as a whole (Guimerà et al., 2005; Newman, 2006).”
BackgroundFood-web structure and network theory: The role of connectance and size
Dunne, J. A., Williams, R. J., & Martinez, N. D. (2002) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.192407699 · Cited by 1,531 · cited 1× · see citing works
“…been used to examine the organization of networks across disparate research foci, including the World Wide Web (Latora and Marchiori, 2001), social networks (Zachary, 1977), the power grid (Watts and Strogatz, 1998), brain processes (Bassett and Bullmore, 2006), and food-webs (Dunne et al., 2002).”
BackgroundFunctional brain networks develop from a local to distributed organization
Fair, D. A., Cohen, A. L., Power, J. D., Dosenbach, N. U. F., Church, J. A., Miezin, F. M., Schlaggar, B. L., & Petersen, S. E. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000381 · Cited by 1,530 · cited 2× · see citing works
“As seen in previous fMRI studies, the correlation matrices contain negative correlations and connection weights that span from near zero to very strong (Fair et al., 2009; Gates et al., 2014).”
BackgroundSelf-citationComputing Communities in Large Networks Using Random Walks
Pons, P., & Matthieu Latapy, B. (2006) · Journal of Graph Algorithms and Applications · doi:10.7155/jgaa.00124 · Cited by 1,505 · see citing works
Barabรกsi, A.-L. (2016) · Cited by 1,375 · see citing works
Finding Statistically Significant Communities in Networks
Lancichinetti, A., Radicchi, F., Ramasco, J. J., & Fortunato, S. (2011) · PLoS ONE · doi:10.1371/journal.pone.0018961 · Cited by 1,195 · cited 2× · see citing works
“We also limited our investigation to algorithms that can accommodate > 75 nodes and do not allow for overlap in communities (such as OSLOM; Lancichinetti et al., 2011).”
BackgroundMethodNetwork Centrality in the Human Functional Connectome
Zuo, X., Ehmke, R. C., Mennes, M., Imperati, D., Castellanos, F. X., Sporns, O., & Milham, M. P. (2011) · Cerebral Cortex · doi:10.1093/cercor/bhr269 · Cited by 1,169 · cited 1× · see citing works
“In following the current state of science and use of correlation matrices with community detection (Zuo et al., 2012; Sporns, 2013), we generate matrices which reflect only the lag-0 relations among brain regions.”
MethodCommunities in NetworksPreprint
Porter, M., Onnela, J., & Mucha, P. (2009) · arXiv.org · doi:10.48550/arxiv.0902.3788 · Cited by 1,122 · cited 3× · see citing works
“It should be noted that modularity has previously been suggested to not be a poor marker of performance (Porter et al., 2009).”
BackgroundInfluentialCooperative Game Theory Approaches for Network Partitioning
Avrachenkov, K. E., Kondratev, A. Y., & Mazalov, V. V. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-62389-4_49 · Cited by 1,075 · see citing works
Network attributes for segregation and integration in the human brain
Sporns, O. (2013) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2012.11.015 · Cited by 1,067 · cited 1× · see citing works
“In following the current state of science and use of correlation matrices with community detection (Zuo et al., 2012; Sporns, 2013), we generate matrices which reflect only the lag-0 relations among brain regions.”
MethodLancichinetti, A., & Fortunato, S. (2009) · Physical Review E · doi:10.1103/physreve.80.016118 · Cited by 1,014 · cited 1× · see citing works
“The average and max degrees increased as graph size increased given the increased number of nodes and were informed by prior studies (Lancichinetti and Fortunato, 2009).”
ResultFunctional system and areal organization of a highly sampled individual human brain
Laumann, T. O., Gordon, E. M., Adeyemo, B., Snyder, A. Z., Joo, S. J., Chen, M.-Y., Gilmore, A. W., McDermott, K. B., Nelson, S. M., Dosenbach, N. U. F., et al. (2015) · Neuron · doi:10.1016/j.neuron.2015.06.037 · Cited by 911 · cited 1× · see citing works
“Increasingly it is becoming apparent that individuals may vary in their functional connectivity across time (Laumann et al., 2015).”
BackgroundWeight-conserving characterization of complex functional brain networks
Rubinov, M., & Sporns, O. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2011.03.069 · Cited by 871 · cited 2× · see citing works
“…has come to be known as the Louvain method (or the “multilevel community method” developed by Blondel and colleagues) similarly utilizes modularity to identify the best partitions but uses a different method than the previously described approaches (Blondel et al., 2008; Rubinov and Sporns, 2011).”
MethodProperties of the Hubert-Arable Adjusted Rand Index.
Steinley, D. (2004) · Psychological Methods · doi:10.1037/1082-989x.9.3.386 · Cited by 763 · cited 1× · see citing works
“Classification rates, a category that MP falls into, may not be the best choice because of the arbitrary distinctions necessary to arrive at what the “correct” placement is (Steinley, 2004).”
BackgroundSelf-citationUncovering Intrinsic Modular Organization of Spontaneous Brain Activity in Humans
Yong He, A., Wang, J., Wang, L. Y., Chen, Z. J., Yan, C., Yang, H., Tang, H., Zhu, C., Gong, Q., Zang, Y., et al. (2009) · PLoS ONE · doi:10.1371/journal.pone.0005226 · Cited by 619 · cited 1× · see citing works
“Given the exceptional performance on large graphs (on the order of thousands), neuroimagers routinely apply community detection algorithms to graphs with node size on the order of hundreds (e.g., Power et al., 2011) and smaller (e.g., He et al., 2009).”
MethodMental Disorders as Causal Systems: A Network Approach to Posttraumatic Stress Disorder
McNally, R. J., Robinaugh, D. J., Wu, G. W. Y., Wang, L., Deserno, M. K., & Borsboom, D. (2015) · Clinical Psychological Science · doi:10.1177/2167702614553230 · Cited by 592 · see citing works
Barabási, A.-Ĺ. (2013) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2012.0375 · Cited by 563 · see citing works
Limits of modularity maximization in community detection
Lancichinetti, A., & Fortunato, S. (2011) · Physical Review E · doi:10.1103/physreve.84.066122 · Cited by 495 · cited 4× · see citing works
“We also limited our investigation to algorithms that can accommodate > 75 nodes and do not allow for overlap in communities (such as OSLOM; Lancichinetti et al., 2011).”
BackgroundMethodInfluentialA tutorial in connectome analysis: Topological and spatial features of brain networks
Kaiser, M. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2011.05.025 · Cited by 371 · cited 1× · see citing works
“Sparse count represent the types of matrices used by researchers examining anatomical connectivity by counting streamlines to arrive at the total number of tracts between two given brain regions (Kaiser, 2011).”
BackgroundConserved and variable architecture of human white matter connectivity
Bassett, D. S., Brown, J. A., Deshpande, V. S., Carlson, J. M., & Grafton, S. T. (2010) · NeuroImage · doi:10.1016/j.neuroimage.2010.09.006 · Cited by 356 · see citing works
Robustness of community structure in networks
Karrer, B., Levina, E., & Newman, M. E. J. (2008) · Physical Review E · doi:10.1103/physreve.77.046119 · Cited by 350 · cited 1× · see citing works
“Obtaining a high modularity may not always reflect that the community structure as defined here was obtained (also see Karrer et al., 2008).”
BackgroundLocal Optima in K-Means Clustering: What You Don't Know May Hurt You.
Steinley, D. (2003) · Psychological Methods · doi:10.1037/1082-989x.8.3.294 · Cited by 270 · cited 1× · see citing works
“An important note is that the algorithm begins by randomly placing individuals into communities; thus multiple runs on the same data may remit different solutions and the ordering may have implications for the reliability of the solution (Steinley, 2003).”
MethodSelf-citationTratt, L. (2008) · Research Portal (King's College London) · doi:10.1007/978-3-540-88643-3-11 · Cited by 250 · see citing works
The effect of size heterogeneity on community identification in complex networks
Danon, L., Dı́az-Guilera, A., & Arenas, À. (2006) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/2006/11/p11010 · Cited by 234 · cited 1× · see citing works
“Modularity has surpassed other metrics in its ability to identify the optimal partition of communities (Danon et al., 2006); however, it comes with limitations such as a reported inability to recover graphs with small communities (Fortunato and Barthélemy, 2007; Porter et al., 2009), different sized…”
BackgroundSchaub, M. T., Delvenne, J., Yaliraki, S. N., & Barahona, M. (2012) · PLoS ONE · doi:10.1371/journal.pone.0032210 · Cited by 149 · cited 1× · see citing works
“To date, few large-scale independent study have compared approaches across numerous varied conditions using simulated data (Schaub et al., 2012), and none have focused on the use of correlation matrices (Pons and Latapy, 2006; Orman and Labatut, 2009; Lancichinetti and Fortunato, 2011, all…”
BackgroundA Comparison of Community Detection Algorithms on Artificial Networks
Orman, G. K., & Labatut, V. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04747-3_20 · Cited by 109 · cited 9× · see citing works
“This follows previous findings on sparse count matrices that indicated Walktrap performs excellently across a range of conditions (Pons and Latapy, 2006; Orman and Labatut, 2009).”
BackgroundMethodResultInfluentialGates, K. M., Molenaar, P. C. M., Iyer, S. P., Nigg, J. T., & Fair, D. A. (2014) · PLoS ONE · doi:10.1371/journal.pone.0091322 · Cited by 107 · cited 1× · see citing works
“As seen in previous fMRI studies, the correlation matrices contain negative correlations and connection weights that span from near zero to very strong (Fair et al., 2009; Gates et al., 2014).”
Self-citationDetecting network modules in fMRI time series: A weighted network analysis approach
Mumford, J. A., Horvath, S., Oldham, M. C., Langfelder, P., Geschwind, D. H., & Poldrack, R. A. (2010) · NeuroImage · doi:10.1016/j.neuroimage.2010.05.047 · Cited by 81 · see citing works
The Identification of Blocs in Small Political Bodies
Rice, S. A. (1927) · American Political Science Review · doi:10.2307/1945514 · Cited by 75 · cited 1× · see citing works
“While work on methods for arriving at community structures in networks began in 1927 (Rice, 1927), there has been a proliferation of techniques in the short time since Girvan and Newman’s seminal paper (Girvan and Newman, 2002).”
Methodclues: AnRPackage for Nonparametric Clustering Based on Local Shrinking
Chang, F.-L., Qiu, W., Zamar, R. H., Lazarus, R. M., & Wang, X. (2010) · Journal of Statistical Software · doi:10.18637/jss.v033.i04 · Cited by 74 · cited 1× · see citing works
“The R package clues was used to calculate ARI HA (Chang et al., 2010).”
MethodOn the equivalence of the label propagation method of community detection and a Potts model approach
Tibély, G., & Kertész, J. (2008) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2008.04.024 · Cited by 68 · cited 2× · see citing works
“It is equivalent to finding the local energy minima of a simple zero-temperature Potts model, but the number of minima is larger than the number of nodes (Tibély and Kertész, 2008).”
BackgroundAccuracy and precision of methods for community identification in weighted networks
Fan, Y., Li, M., Zhang, P., Wu, J., & Di, Z. (2006) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2006.11.036 · Cited by 52 · cited 1× · see citing works
“Formally, modularity for weighted networks can be written as (Fan et al., 2007): with δ being 1 if the nodes belong to the same community and 0 if otherwise.”
Background
Flagged first, then by citations
1 of the 59 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- Sporns O. (2011). Networks of the Brain. Cambridge, MA: Massachusetts Institute of Technology.
Cited by
Sorted by citations
Golino, H. F., Shi, D., Christensen, A. P., Garrido, L. E., Nieto, M. D., Sadana, R., Thiyagarajan, J. A., & Martínez‐Molina, A. (2020) · Psychological Methods · doi:10.1037/met0000255 · Cited by 550 · see citing works
The Heterogeneity Problem: Approaches to Identify Psychiatric Subtypes
Feczko, E., Miranda-Dominguez, O., Marr, M., Graham, A. M., Nigg, J. T., & Fair, D. A. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2019.03.009 · Cited by 443 · see citing works
“The technique is robust to many case scenarios[87].”
BackgroundMethodSelf-citationGrayson, D. S., & Fair, D. A. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.01.079 · Cited by 411 · see citing works
“In the case of identified networks in infants it is important to note that different community detection algorithms can provide unique results and all are not appropriate for any given experimental condition (Gates et al., 2016).”
BackgroundSelf-citationChristensen, A. P., & Golino, H. F. (2021) · Psych · doi:10.3390/psych3030032 · Cited by 358 · see citing works
Dalege, J., Borsboom, D., van Harreveld, F., & van der Maas, H. L. J. (2017) · Social Psychological and Personality Science · doi:10.1177/1948550617709827 · Cited by 251 · see citing works
“We use the walktrap algorithm (Pons & Latapy, 2005), as this algo-rithm performs well on psychological networks (Gates, Henry, Steinley, & Fair, 2016; Golino & Epskamp, 2016).”
MethodPluralistic Collapse: The “Oil Spill” Model of Mass Opinion Polarization
DellaPosta, D. (2020) · American Sociological Review · doi:10.1177/0003122420922989 · Cited by 219 · see citing works
Subtyping cognitive profiles in Autism Spectrum Disorder using a Functional Random Forest algorithm
Feczko, E., Balba, N. M., Miranda-Dominguez, O., Cordova, M., Karalunas, S. L., Irwin, L., Demeter, D. V., Hill, A. P., Langhorst, B. H., Grieser Painter, J., et al. (2018) · NeuroImage · doi:10.1016/j.neuroimage.2017.12.044 · Cited by 173 · see citing works
Self-citationUncovering general, shared, and unique temporal patterns in ambulatory assessment data.
Lane, S., Gates, K. M., Pike, H., Beltz, A. M., & Wright, A. G. C. (2018) · Psychological Methods · doi:10.1037/met0000192 · Cited by 136 · see citing works
Self-citationUnsupervised Classification During Time-Series Model Building
Gates, K. M., Lane, S., Varangis, E. M. L., Giovanello, K. S., & Guiskewicz, K. (2016) · Multivariate Behavioral Research · doi:10.1080/00273171.2016.1256187 · Cited by 136 · see citing works
Self-citationComparing community detection algorithms in psychometric networks: A Monte Carlo simulation
Christensen, A. P., Garrido, L. E., Guerra-Peña, K., & Golino, H. F. (2023) · Behavior Research Methods · doi:10.3758/s13428-023-02106-4 · Cited by 184 · see citing works
“Then, the algorithm collapses the communities into latent nodes and identifies edge weights with other observed and latent nodes, which provides the “multi-level” structure (Gates et al., 2016).”
InfluentialWright, A. G. C., Gates, K. M., Arizmendi, C., Lane, S., Woods, W. C., & Edershile, E. A. (2019) · Psychological Assessment · doi:10.1037/pas0000617 · Cited by 107 · see citing works
Self-citationA precision functional atlas of personalized network topography and probabilities
Hermosillo, R. J. M., Moore, L. A., Feczko, E., Miranda-Domínguez, Ó., Pines, A. R., Dworetsky, A., Conan, G. M., Mooney, M. A., Randolph, A., Graham, A. M., et al. (2024) · Nature Neuroscience · doi:10.1038/s41593-024-01596-5 · Cited by 87 · see citing works
“Neural network graphs can be mapped at multiple scales, and the reliability when resolving network assignments at those scales can vary depending on the dataset and the community detection algorithm 117 .”
BackgroundSelf-citationRozgonjuk, D., Sindermann, C., Elhai, J. D., Christensen, A. P., & Montag, C. (2020) · Journal of Behavioral Addictions · doi:10.1556/2006.2020.00036 · Cited by 82 · see citing works
Golino, H. F., Christensen, A. P., Moulder, R. G., Jr., Kim, S., & Boker, S. M. (2021) · Psychometrika · doi:10.1007/s11336-021-09820-y · Cited by 63 · see citing works
“The number of steps can be specified by the user; however, EGA uses the default of 4, which has been shown to be optimal for the number of variables typically used in psychological research (Christensen, 2020; Gates, Henry, Steinley, & Fair, 2016).”
MethodHow does AI drive branding? Towards an integrated theoretical framework for AI-driven branding
Deryl, M. D., Verma, S., & Srivastava, V. (2023) · International Journal of Information Management Data Insights · doi:10.1016/j.jjimei.2023.100205 · Cited by 72 · see citing works
Comparing community detection algorithms in psychological data: A Monte Carlo simulationPreprint
Christensen, A. P., Garrido, L. E., Guerra-Peña, K., & Golino, H. F. (2020) · doi:10.31234/osf.io/hz89e · Cited by 60 · see citing works
Sahdra, B. K., Ciarrochi, J., Fraser, M. I., Yap, K., Haller, E., Hayes, S. C., Hofmann, S. G., & Gloster, A. T. (2023) · Mindfulness · doi:10.1007/s12671-023-02187-4 · Cited by 63 · see citing works
“High frequency longitudinal data (>60 time points) are needed for such approaches to produce reliable estimates (Gates et al., 2016).”
BackgroundAbnormal meta-state activation of dynamic brain networks across the Alzheimer spectrum
Nùñez, P., Poza, J., Gómez, C., Rodríguez-González, V., Hillebrand, A., Tewarie, P. K. B., Tola-Arribas, M. Á., Cano, M., & Hornero, R. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.117898 · Cited by 52 · see citing works
“Spectral Approach, Infomap, Label Propagation or non-backtracking matrix (Gates et al. (2016); Krzakala et al. (2013)), lead to similar results.”
InfluentialMiers, A. C., Weeda, W. D., Blöte, A. W., Cramer, A. O. J., Borsboom, D., & Westenberg, P. M. (2019) · Journal of Abnormal Psychology · doi:10.1037/abn0000484 · Cited by 47 · see citing works
Corponi, F., Anmella, G., Verdolini, N., Pacchiarotti, I., Samalin, L., Popović, D., Azorin, J., Angst, J., Bowden, C. L., Mosolov, S. N., et al. (2020) · European Neuropsychopharmacology · doi:10.1016/j.euroneuro.2020.03.017 · Cited by 39 · see citing works
Mills, B. D., Grayson, D. S., Shunmugavel, A., Miranda-Domínguez, Ó., Feczko, E., Earl, E., Neve, K. A., & Fair, D. A. (2018) · Journal of Neuroscience · doi:10.1523/jneurosci.2910-17.2018 · Cited by 36 · see citing works
Self-citationthe CALM team, Mareva, S., & Holmes, J. (2019) · BMC Pediatrics · doi:10.1186/s12887-019-1818-7 · Cited by 35 · see citing works
Leonhard, C. (2023) · Neuropsychology Review · doi:10.1007/s11065-023-09601-7 · Cited by 34 · see citing works
“However, when an actual data set is not available, as is the case here, researchers in neuropsychology use hypothetical data sets to evaluate the performance of classification algorithms (e.g., Gates et al., 2016; Underwood et al., 2018), which is the approach taken here.”
MethodSahdra, B. K., Ciarrochi, J., Klimczak, K. S., Krafft, J., Hayes, S. C., & Levin, M. E. (2024) · Journal of Contextual Behavioral Science · doi:10.1016/j.jcbs.2024.100728 · Cited by 35 · see citing works
“…methods a large number of within-person observations (~100) are needed to obtain reliable within-person estimates from individual networks and a large number of individuals ( > 500) are needed to accurately recover known paths in networks of subgroups (Gates, Henry, Steinley, & Fair, 2016).”
Introducing a science interest network model to reveal country differences.
Sachisthal, M. S. M., Jansen, B. R. J., Peetsma, T. T. D., Dalege, J., van der Maas, H. L. J., & Raijmakers, M. E. J. (2019) · Journal of Educational Psychology · doi:10.1037/edu0000327 · Cited by 32 · see citing works
Schreiber, J., Scherrer, A., & Breetz, H. L. (2023) · Energy Research & Social Science · doi:10.1016/j.erss.2023.103193 · Cited by 28 · see citing works
Sanchez-Rodriguez, L. M., Iturria‐Medina, Y., Mouchès, P., & Sotero, R. C. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.117431 · Cited by 25 · see citing works
Post-traumatic stress disorder and depressive symptoms among firefighters: a network analysis
Cheng, P., Wang, L., Zhou, Y., Ma, W., Zhao, G., Zhang, L., & Li, W. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1096771 · Cited by 24 · see citing works
Preszler, J. R., & Burns, G. L. (2019) · Research on Child and Adolescent Psychopathology · doi:10.1007/s10802-019-00549-y · Cited by 24 · see citing works
Assessing the robustness of cluster solutions obtained from sparse count matrices.
Gates, K. M., Fisher, Z. F., Arizmendi, C., Henry, T. R., Duffy, K. A., & Mucha, P. J. (2019) · Psychological Methods · doi:10.1037/met0000204 · Cited by 23 · see citing works
Self-citationDarius, P. (2022) · Social Network Analysis and Mining · doi:10.1007/s13278-022-00958-w · Cited by 22 · see citing works
García-Pardina, A., Abad, F. J., Christensen, A. P., Golino, H. F., & Garrido, L. E. (2024) · Behavior Research Methods · doi:10.3758/s13428-024-02348-w · Cited by 24 · see citing works
“…hierarchically, starting with smaller clusters or sets of nodes and merging them into larger and larger clusters by optimizing a criterion called modularity (the extent to which nodes are more connected to nodes within their community than to nodes in other communities; Gates et al., 2016).”
Simpson-Kent, I. L., Fried, E. I., Akarca, D., Mareva, S., Bullmore, E. T., the CALM Team, & Kievit, R. (2021) · Journal of Intelligence · doi:10.3390/jintelligence9020032 · Cited by 21 · see citing works
“…literature and, in a Monte Carlo simulation study, was shown to outperform other algorithms (e.g. InfoMap) for sparse count networks (e.g. those used in diffusion tensor imaging), although it must be noted that this result was for networks made up of 500 nodes or higher (Gates et al., 2016).”
MethodGolino, H. F., Thiyagarajan, J. A., Sadana, R., Santos, M. T., Christensen, A. P., & Boker, S. M. (2020) · doi:10.31234/osf.io/hj5mc · Cited by 21 · see citing works
Mareva, S., Akarca, D., The CALM team, & Holmes, J. (2022) · Journal of Child Psychology and Psychiatry · doi:10.1111/jcpp.13685 · Cited by 20 · see citing works
On maximization of the modularity index in network psychometrics
Brusco, M. J., Steinley, D., & Watts, A. L. (2022) · Behavior Research Methods · doi:10.3758/s13428-022-01975-5 · Cited by 23 · see citing works
“These analyses are important because recent comparative simulation studies in the psychological literature (i.e., Christensen et al., 2021; Gates et al., 2016; Hoffman et al., 2018) did not evaluate maximization of Q in their simulation experiments.”
BackgroundMethodInfluentialSelf-citationPellegrini, V. (2023) · PLoS ONE · doi:10.1371/journal.pone.0280285 · Cited by 21 · see citing works
KO: Modularity optimization in community detection
Öztemız, F., & Karcı, A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08284-8 · Cited by 20 · see citing works
“In the first iteration, nodes 56, 6, 44, 48, 20, 12, 57, 67, 49, 37, 38 were added to the transfer list, since the transfer of nodes 56, 6, 44, 48, 20, and 67 from these nodes increased the modularity value, the transfer was approved, and as a result of the first iteration, the modularity value…”
BackgroundMethodNùñez, P., Gómez, C., Rodríguez-González, V., Hillebrand, A., Tewarie, P. K. B., Gómez‐Pilar, J., Molina, V., Hornero, R., & Poza, J. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac514e · Cited by 17 · see citing works
“However, there are a variety of community detection algorithms available, with their own advantages and disadvantages, which could be assessed in future studies (Gates et al 2016).”
InfluentialTowards personalized precision functional mapping in infancy
Moore, L. A., Hermosillo, R. J. M., Feczko, E., Moser, J., Koirala, S., Allen, M. C., Buß, C., Conan, G., Juliano, A., Marr, M. C., et al. (2024) · Imaging Neuroscience · doi:10.1162/imag_a_00165 · Cited by 17 · see citing works
“…et al., 2018; Laumann et al., 2015; Newbold et al., 2020), followed by application of Infomap, a powerful data-driven community detection method, to reliably define individual network topology ( Gates et al., 2016; Lancichinetti & Fortunato, 2009; Power et al., 2011; Rosvall & Bergstrom, 2008).”
MethodSelf-citationRodríguez-González, V., Nùñez, P., Gómez, C., Hoshi, H., Shigihara, Y., Hornero, R., & Poza, J. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105512 · Cited by 15 · see citing works
Ye, A., Gates, K. M., Henry, T. R., & Luo, L. (2021) · Psychometrika · doi:10.1007/s11336-021-09753-6 · Cited by 14 · see citing works
“Although the forward-selection method for uSEM model has been shown effective when applied to fMRI studies (e.g., Gates et al., 2016), it is not without issues as are all stepwise approaches.”
MethodSelf-citationOptimizing Walktrap’s Community Detection in Networks Using the Total Entropy Fit IndexPreprint
Jamison, L., Christensen, A. P., & Golino, H. F. (2021) · doi:10.31234/osf.io/9pj2m · Cited by 16 · see citing works
Subgrouping with Chain Graphical VAR Models
Park, J., Chow, S., Epskamp, S., & Molenaar, P. C. M. (2024) · Multivariate Behavioral Research · doi:10.1080/00273171.2023.2289058 · Cited by 13 · see citing works
“…community detection method which operates by maximizing the modularity of a given network; however, modularity maximization has frequently been criticized due to issues related to its ability to enumerate smaller communities when networks are comprised of varying sizes (Gates et al., 2016).”
BackgroundKramer, S. J., Maritorena, S., Cetinić, I., Werdell, P. J., & Siegel, D. A. (2024) · Optics Express · doi:10.1364/oe.529906 · Cited by 14 · see citing works
DSEAGC: Dual-spectral embedding for attributed graph clustering
Zhao, Y., Liang, W., Gong, Z., Sun, S., & Nejadshamsi, S. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101651 · Cited by 14 · see citing works
Unidimensional community detection: A monte carlo simulation, grid search, and comparison.
Christensen, A. P. (2024) · Psychological Methods · doi:10.1037/met0000692 · Cited by 14 · see citing works
The form and evolution of international migration networks, 1990–2015
Abel, G., DeWaard, J., Ha, J. T., & Almquist, Z. W. (2021) · Population Space and Place · doi:10.1002/psp.2432 · Cited by 13 · see citing works
Xavier, J., & Picoto, W. (2023) · International Journal of Law and Management · doi:10.1108/ijlma-02-2023-0022 · Cited by 11 · see citing works
Improving the Walktrap Algorithm Using K -Means Clustering
Brusco, M. J., Steinley, D., & Watts, A. L. (2024) · Multivariate Behavioral Research · doi:10.1080/00273171.2023.2254767 · Cited by 12 · see citing works
“…method in psychological research because of its performance in simulation studies (Brusco, Steinley et al., 2022a, 2022b; Christensen et al., 2023; Gates et al., 2016; Golino et al., 2020, 2021; Hoffman et al., 2018) and its use in applied research (Dalege et al., 2017; Kendler et al., 2018;…”
BackgroundMethodSelf-citationConcordance networks and application to clustering cancer symptomology
Henry, T. R., Marshall, S. A., Avis, N. E., Levine, B. J., & Ip, E. H. (2018) · PLoS ONE · doi:10.1371/journal.pone.0191981 · Cited by 12 · see citing works
Self-citationMultisource Longitudinal Network and Latent Variable Model Analyses of ADHD Symptoms in Children
Preszler, J. R., Burns, G. L., Becker, S. P., & Servera, M. (2020) · Journal of Clinical Child & Adolescent Psychology · doi:10.1080/15374416.2020.1756297 · Cited by 11 · see citing works
“Walktrap was used due to its applicability to psychological networks in particular (Gates et al., 2016).”
MethodMcCormick, E. M., Gates, K. M., & Telzer, E. H. (2018) · NeuroImage · doi:10.1016/j.neuroimage.2018.12.042 · Cited by 11 · see citing works
“Walktrap provides a powerful method for partitioning data into representative subgroups without relying on significance testing (see Gates et al., 2016), which is notoriously difficult in network contexts.”
InfluentialSelf-citationvan der Tuin, S., Groen, R. N., Castro‐Alvarez, S., Oldehinkel, A. J., Booij, S. H., & Wigman, J. T. W. (2021) · Schizophrenia Bulletin Open · doi:10.1093/schizbullopen/sgab047 · Cited by 10 · see citing works
“…were based on the Walktrap algorithm, and the significance criteria for pruning of paths was set with a Bonferroni correction at α = .05/N. 16 38 The group-level-criterion was set at 75%, 18,39 meaning that to be included in the group-level network, adding an edge should improve model fit…”
Demidenko, M. I., Huntley, E. D., Weigard, A. S., Keating, D. P., & Beltz, A. M. (2022) · Journal of Neuroscience Research · doi:10.1002/jnr.25005 · Cited by 9 · see citing works
Christensen, A. P. (2020) · doi:10.31234/osf.io/84kgd · Cited by 12 · see citing works
Stout, D. M., Harlé, K. M., Norman, S. B., Simmons, A. N., & Spadoni, A. D. (2021) · Psychological Medicine · doi:10.1017/s0033291721001513 · Cited by 9 · see citing works
Barboza-Salerno, G., Kosloski, A. E., Weir, H., Thompson, D., & Bukreyev, A. (2022) · Journal of Interpersonal Violence · doi:10.1177/08862605221127222 · Cited by 9 · see citing works
“, 2016) and is considered one of the most reliable forms of community detection (Gates et al., 2016; Pons & Latapy, 2005).”
BackgroundMethodClinical subtyping using community detection: Limited utility?
van Rentergem, J. A. A., Bathelt, J., & Geurts, H. M. (2022) · International Journal of Methods in Psychiatric Research · doi:10.1002/mpr.1951 · Cited by 9 · see citing works
“Walktrap does badly by tending to inappropriately find two to three subtypes.”
BackgroundMethodInfluentialUncovering general, shared, and unique temporal patterns in ambulatory assessment dataPreprint
Lane, S., Gates, K. M., Pike, H., Beltz, A. M., & Wright, A. G. C. (2018) · doi:10.31234/osf.io/d3nk9 · Cited by 14 · see citing works
Self-citationWright, A. G. C., Gates, K. M., Arizmendi, C., Lane, S., Woods, W., & Edershile, E. A. (2017) · doi:10.31219/osf.io/nf5me · Cited by 12 · see citing works
Self-citationMultidomain concussion symptoms in adolescents: A network analysis
Preszler, J. R., Manderino, L. M., Fazio-Sumrok, V., Eagle, S. R., Holland, C. L., Collins, M. W., & Kontos, A. P. (2022) · Applied Neuropsychology Child · doi:10.1080/21622965.2022.2099742 · Cited by 8 · see citing works
A maximal-clique-based set-covering approach to overlapping community detection
Brusco, M. J., Steinley, D., & Watts, A. L. (2023) · Optimization Letters · doi:10.1007/s11590-023-02054-0 · Cited by 8 · see citing works
“Studies comparing these methods for modestly-sized networks (fewer than 100 vertices) encountered in the psychological sciences, have been undertaken by several authors [6, 19, 20].”
Self-citationFrom clubs to hubs: analysing lobbying networks in EU financial regulation after crisis
Redert, B. (2022) · Journal of Public Policy · doi:10.1017/s0143814x21000283 · Cited by 8 · see citing works
“The Walktrap algorithm outperforms other algorithms on a number of key metrics (identifying both large and small networks, sensitivity to the total number of elements, or nodes, under consideration, etc.), and is thus a robust way of detecting communities in the networks (Gates et al. 2016).”
MethodRodríguez-González, V., Nùñez, P., Gómez, C., Shigihara, Y., Hoshi, H., Tola-Arribas, M. Á., Cano, M., Peral, Á. L. G., García‐Azorín, D., Hornero, R., et al. (2023) · NeuroImage · doi:10.1016/j.neuroimage.2023.120332 · Cited by 7 · see citing works
Strigo, I. A., Spadoni, A. D., & Simmons, A. N. (2022) · Frontiers in Pain Research · doi:10.3389/fpain.2022.871961 · Cited by 7 · see citing works
“Furthermore, unsupervised SGIMME uses unsupervised community detection [Walktrap; (56, 57)] on the similarity matrix derived from the individuallevel estimates of the group-level connections to identify an optimal number of subgroups who have similar connectivity profiles.”
MethodProximity within adolescent peer networks predicts neural similarity during affective experience
Feldman, M. J., Capella, J., Dai, J., Bonar, A. S., Field, N. H., Lewis, K., Prinstein, M. J., Telzer, E. H., & Lindquist, K. A. (2024) · Social Cognitive and Affective Neuroscience · doi:10.1093/scan/nsae072 · Cited by 7 · see citing works
“For exploratory analyses (these analyses were not preregistered), the igraph package was also used to perform community detection and assign individuals to clusters via the walktrap method, which has been shown to perform well in smaller and denser networks (Gates et al. 2016).”
MethodMerritt, S. H., & Christensen, A. P. (2023) · Advances in Artificial Intelligence and Machine Learning · doi:10.54364/aaiml.2023.1149 · Cited by 6 · see citing works
“There are many different community detection algorithms with some of the more commonly applied algorithms being the Walktrap [20] and Louvain [9, 11, 21, 22, 23].”
MethodDisrupted temporal structure of the M/EEG meta-states sequencing in Alzheimer’s disease
Sandonís-Fernández, M., Nùñez, P., Tola-Arribas, M. Á., Cano, M., Hoshi, H., Shigihara, Y., Poza, J., & Gómez, C. (2025) · NeuroImage · doi:10.1016/j.neuroimage.2025.121555 · Cited by 5 · see citing works
A Gentle Introduction and Application of Feature-Based Clustering with Psychological Time Series
Kreienkamp, J., Agostini, M., Monden, R., Epstude, K., de Jonge, P., & Bringmann, L. F. (2024) · Multivariate Behavioral Research · doi:10.1080/00273171.2024.2432918 · Cited by 4 · see citing works
“…algorithms like Walktrap, which operate on similarity measures derived from correlation matrices, can actually benefit from higher-dimensional data because more features lead to more robust and accurate similarity estimates between participants (e.g., Gates et al., 2016; Golino & Epskamp, 2017).”
Two sample tests for high-dimensional autocovariances
Baek, C., Gates, K. M., Leinwand, B., & Pipiras, V. (2020) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2020.107067 · Cited by 5 · see citing works
Self-citationClustering Individuals Based on Similarity in Idiographic Factor Loading Patterns
Arizmendi, C., & Gates, K. M. (2024) · Multivariate Behavioral Research · doi:10.1080/00273171.2024.2374826 · Cited by 4 · see citing works
“Walktrap has shown good performance with both count and correlation matrices (Gates et al., 2016; Golino & Epskamp, 2017) and has outperformed more classic clustering algorithms, in particular DIANA (Ferreira & Zhao, 2016).”
Self-citationChristensen, A. P. (2020) · doi:10.31237/osf.io/7u9bn · Cited by 4 · see citing works
Network Accuracy Across Local, Mesoscale, and Global Structures using Stochastic Block ModelsPreprint
Christensen, A. P., & Choi, J. (2024) · doi:10.31234/osf.io/9d4nm · Cited by 4 · see citing works
Electroencephalogram-Based Metastability in Mild Cognitive Impairment Alzheimer's Disease
Das, S. S., & Puthankattil, S. D. (2023) · Brain Connectivity · doi:10.1089/brain.2023.0041 · Cited by 3 · see citing works
“Furthermore, the properties of metastable activation patterns were studied through rapidly changing brain connectivity patterns through the Louvain GJA community detection al-gorithm (Gates et al., 2016).”
Exploring Estimation Procedures for Reducing Dimensionality in Psychological Network Modeling
Shi, D., Christensen, A. P., Day, E. A., Golino, H. F., & Garrido, L. E. (2024) · Multivariate Behavioral Research · doi:10.1080/00273171.2024.2395941 · Cited by 7 · see citing works
“Second, the Louvain has the advantage of detecting hierarchical structures ( Blondel et al., 2008; Gates et al., 2016; Jim � enez et al., 2023).”
The network structure of mania symptoms differs between people with and without binge eating
Davies, H. L., Peel, A. J., Mundy, J., Monssen, D., Kakar, S. A., Davies, M. R., Adey, B. N., Armour, C., Kalsi, G., Lin, Y., et al. (2023) · Bipolar Disorders · doi:10.1111/bdi.13355 · Cited by 3 · see citing works
“36 Age and sex were forced into their own cluster named ‘covariates’.”
BackgroundMethodRegression and alignment for functional data and network topology.
Tu, D., Wrobel, J., Satterthwaite, T., Goldsmith, J., Gur, R. C., Gur, R., Gertheiss, J., Bassett, D. S., & Shinohara, R. (2024) · Biostatistics · doi:10.1093/biostatistics/kxae026 · Cited by 1 · see citing works
Topluluk Tespiti Yöntemi ile Ulaşım Ağında Verimli Yeşil Dalga Koridorlarının Belirlenmesi
Öztemız, F., & Karcı, A. (2024) · Journal of Polytechnic · doi:10.2339/politeknik.1074962 · Cited by 3 · see citing works
Altered electrophysiological meta-state dynamics in disorders of consciousness
Nùñez, P., Tewarie, P. K. B., Rodríguez-González, V., Alnagger, N., van der Lande, G., Vitello, M. M., Cardone, P., Thibaut, A., Belloli, L. M. L., Laureys, S., et al. (2025) · NeuroImage · doi:10.1016/j.neuroimage.2025.121519 · Cited by 2 · see citing works
Revisiting the IPIP-NEO personality hierarchy with taxonomic graph analysis
Samo, A., Garrido, L. E., Abad, F. J., Golino, H. F., McAbee, S. T., & Christensen, A. P. (2025) · European Journal of Personality · doi:10.1177/08902070251352590 · Cited by 3 · see citing works
“…(Blondel et al., 2008), has been demonstrated to be one of the more accurate dimension recovery algorithms across a variety of data generating conditions (e.g., count, latent factors, Lancichinetti-Fortunato-Radicchi graphs; Christensen et al., 2024; Gates et al., 2016; Yang et al., 2016).”
Blind Subgrouping of Task-based FMRI
Fisher, Z. F., Parsons, J., Gates, K. M., & Hopfinger, J. B. (2023) · Psychometrika · doi:10.1007/s11336-023-09907-8 · Cited by 2 · see citing works
“Walktrap has been found to perform well on networks with a range of characteristics, including count and correlation matrices as well as small and large networks (Gates et al., 2016; Golino & Epskamp, 2017).”
BackgroundSelf-citationSocial anxiety and concordance in emotional responses across levels of evaluative threatPreprint
Toner, E. R., Larrazabal, M. A., Cai, L., Henry, T. R., MacCormack, J. K., Boukhechba, M., Barnes, L. E., & Teachman, B. A. (2022) · doi:10.31234/osf.io/wbfp8 · Cited by 2 · see citing works
Self-citationZengin, H. Y., & Karabulut, E. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05540-5 · Cited by 1 · see citing works
“Although the measures used to define the interaction between genes differ among studies [5, 30–32], similarity measures are often used for this purpose.”
BackgroundDuxbury, S. (2024) · Social Forces · doi:10.1093/sf/soae052 · Cited by 1 · see citing works
CDSE: Consensus-based dual-spectral embedding for attributed graph clustering
Wang, Y., & Wang, J. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08049-1 · Cited by 1 · see citing works
“Random walk-based approaches use random walkers to identify dense regions in a network, with notable algorithms including MCL [34], Walktrap [35], and Infomap [36].”
Giacomo, R. D., Nùñez, P., Poza, J., Rodríguez-González, V., Gomez, C., Burini, A., Castana, L., de Curtis, M., Tassi, L., & Varotto, G. (2026) · Brain Communications · doi:10.1093/braincomms/fcag047 · Cited by 1 · see citing works
“The Louvain GJA algorithm performs community segmentation maximizing modularity 42,52 and reveals groups of time windows that are similar to others, 7 The community detection was individually performed for each patient, as the different number and spatial locations of SEEG electrodes prevented the…”
Kramer, S. J. (2026) · Environmental Microbiology · doi:10.1111/1462-2920.70416 · Cited by 1 · see citing works
“When only one field campaign was considered at a time, the shape of the relationship captured one side or the other of the classic unimodal curve found in a global dataset (Acevedo-Trejos et al. 2018; Ibarbalz et al. 2019).”
Nùñez, P., Rodríguez-González, V., Pablo, V. G.-D., Gómez, C., Shigihara, Y., Hoshi, H., Hornero, R., & Poza, J. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630583 · Cited by 1 · see citing works
“Nonetheless, this could also be due to inherent limitations of the community detection algorithm, as they usually perform better with larger graph sizes [12].”
BackgroundMethodSensitivity of Clustering Algorithms to Sparseness of One Correlation Network
Timofeeva, A., & Gorbacheva, N. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36625-3_26 · Cited by 1 · see citing works
Dynamic Brain Functional Networks to Investigate Protective Mechanisms Against Epileptic Seizures
Varotto, G., Nùñez, P., Giacomo, R. D., Poza, J., Burini, A., Rodriguez, V., Gómez, C., Castana, L., de Curtis, M., & Tassi, L. (2024) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine62247.2024.10796533 · Cited by 1 · see citing works
“Then, the Louvain GJA community detection algorithm [12] was applied to the RPs, without a priori specifying the number of communities to be detected [13].”
Hwang, T., Choi, S. J., & Lee, J. (2025) · Digital Health · doi:10.1177/20552076251375930 · Cited by 1 · see citing works
Butter, S. (2020) · Ulster University Research Portal (Ulster University) · Cited by 1 · see citing works
Brusco, M. J., Steinley, D., & Watts, A. L. (2020) · doi:10.31234/osf.io/2qw79 · Cited by 1 · see citing works
Self-citationLongitudinal Network Re-organization Across Learning and DevelopmentPreprint
McCormick, E. M., Peters, S., Crone, E. A., & Telzer, E. H. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.10.23.353094 · Cited by 1 · see citing works
Patel, V. (2019) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.735861475.793563123
A Study Partner Recommender System Using a Community Detection Algorithm
Obionwu, C. V., Ilapavuluri, D. P., Broneske, D., & Saake, G. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-67904-9_5
Integer programming in psychology: A review and directions for future research
Brusco, M. J., Steinley, D., & Watts, A. L. (2025) · British Journal of Mathematical and Statistical Psychology · doi:10.1111/bmsp.12386
Self-citationOh, H. J., & Wu, T. (2025) · Journal of Psychoeducational Assessment · doi:10.1177/07342829251359360
“Designed to detect multilevel hierarchical structures within large networks, Louvain is particularly suited for analyzing complex datasets (Christensen et al., 2023; Gates et al., 2016).”
- Authors
- Gates, K. M., Henry, T., Steinley, D., & Fair, D. A.
- Affiliations
- University of North Carolina at Chapel Hill (US)
- University of Missouri (US)
- Oregon Health & Science University (US)
- Corresponding author
- Gates, Kathleen M.
- Venue
- Frontiers in Neuroinformatics
- Publisher
- Frontiers Media SA
- Published
- 2016-11-10
- Volume
- 10
- Pages
- 45-45
- ISSN
- 1662-5196 (ISSN-L)
- PMC
- PMC5102890
- OpenAlex
- W2554748751
- Cited by
- 106
- References
- 59
- Citations by year
- 2026: 7 · 2025: 9 · 2024: 19 · 2023: 18 · 2022: 11 · 2021: 10 · 2020: 14 · 2019: 7 · 2018: 6 · 2017: 4 · 2016: 1
- FWCI
- 3.40
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Frontiers in Neuroinformatics (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Carolina Digital Repository (University of North Carolina at Chapel Hill) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- UNC Libraries
- Funders
- National Institute of Biomedical Imaging and Bioengineering (R21 EB015573-01A1)
- National Institute on Alcohol Abuse and Alcoholism (R21 AA022074-02)
- National Institutes of Health
- Topics
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
- Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Clustering Algorithms Research
- Keywords
- community detection, weighted graphs, functional connectivity, brain networks, Louvain method, label propagation, modularity optimization, spectral clustering, diffusion tensor imaging, Monte Carlo simulation, algorithm comparison
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
