eXascaleInfolab / daoc

DAOC (Deterministic and Agglomerative Overlapping Clustering algorithm): Stable Clustering of Large Networks

DAOC - Deterministic and Agglomerative Overlapping Clustering algorithm

\authors (c) Artem Lutov [e-mail]
\license Apache 2.0 with the exception of several files having MPL 2.0 license specified in their headers, optional commercial support and relicensing is provided by the request
\organizations eXascale Infolab, Lumais
\keywords stable clustering, overlapping clustering, com- munity structure discovery, parameter-free community detection, cluster analysis

The paper:

@inproceedings{Daoc19,
	author={Artem Lutov and Mourad Khayati and Philippe Cudr{\'e}-Mauroux},
	title={DAOC: Stable Clustering of Large Networks},
	year={2019},
	keywords={stable clustering, overlapping clustering, community structure discovery, parameter-free community detection, cluster analysis},
}

The source code is being prepared for the publication and cross-platform deployment, and will be fully uploaded soon...
Meanwhile, please write me to get the sources. The DAOC binaries built on Linux Ubuntu 16.04+ x64 can be found in the Clubmark benchmarking framework.

Related Projects

• resmerge - Resolution levels clustering merger with filtering. Flattens hierarchy/list of multiple resolutions levels (clusterings) into the single flat clustering with clusters on various resolution levels synchronizing the node base.
• DAOR - Parameter-free Embedding Framework for Large Graphs (Networks) based on DAOC.
• Clubmark - A parallel isolation framework for benchmarking and profiling clustering (community detection) algorithms considering overlaps (covers), includes a dozen of clustering algorithms for large networks.
• ParallelComMetric - A parallel toolkit implemented with Pthreads (or MPI) to calculate various extrinsic and intrinsic quality metrics (with and without ground truth community structure) for non-overlapping (hard, single membership) clusterings.
• CluSim - A Python module that evaluates (slowly) various extrinsic quality metrics (accuracy) for non-overlapping (hard, single membership) clusterings.
• GraphEmbEval - Graph (Network) Embeddings Evaluation Framework via classification, which also provides gram martix construction for links prediction.
• xmeasures - Extrinsic quality (accuracy) measures evaluation for the overlapping clustering on large datasets: family of mean F1-Score (including clusters labeling), Omega Index (fuzzy version of the Adjusted Rand Index) and standard NMI (for non-overlapping clusters).
• GenConvNMI - Overlapping NMI evaluation that is compatible with the original NMI and suitable for both overlapping and multi resolution (hierarchical) clustering evaluation.
• OvpNMI - NMI evaluation for the overlapping clusters (communities) that is not compatible with the standard NMI value unlike GenConvNMI, but it is much faster than GenConvNMI.
• ExecTime - A lightweight resource consumption profiler.

See also eXascale Infolab GitHub repository and our website where you can find another projects and research papers related to Big Data processing!

Note: Please, star this project if you use it.