• MIMOSA: Codes (Matlab) for multilayer spectral graph clustering via convex layer aggregation

Task: Cluster the nodes into groups of high similarity based on their multilayer graph connectivity (e.g., each layer refers to one type of relations among a set of common nodes)

Ref: “Multilayer Spectral Graph Clustering via Convex Layer Aggregation: Theory and Algorithms,” IEEE Transactions on Signal and Information Processing over Networks, 2017

  • Deep Community Detection: Codes (Matlab) for detecting deep communities via node and edge removals using local Fiedler vector centrality (LFVC)

Task: Identify deep communities hidden in networks by effective node or edge removals based on LFVC

Ref: "Deep Community Detection", IEEE Tran. Signal Processing 2015

Ref: "Local Fiedler Vector Centrality for Detection of Deep and Overlapping Communities in Networks" IEEE ICASSP 2014

  • Incremental-IO: Codes (Matlab) for incremental eigenpair computation for graph Laplacian matrices [Updated Feb. 2016]

Task: Computation time comparison of sequential smallest eigenpair between the batch method, the proposed incremental method (Incremental-IO), and the adapted Lanczos algorithm (Lanczos-IO)

Ref: “Incremental Eigenpair Computation for Graph Laplacian Matrices: Theory and Applications,” Social Network Analysis and Mining, 2018

  • AMOS: Codes in Python and Matlab (per requested) for AMOS: an automated model order selection algorithm for graph clustering / community detection

Task: Simply input a graph (sparse format is preferred) and AMOS will output reliable clustering results via automated clustering selection and multi-stage statistical testing

Ref: "Phase Transitions and a Model Order Selection Criterion for Spectral Graph Clustering", IEEE Tran. Signal Processing 2018

Ref: "AMOS: An Automated Model Order Selection Algorithm for Spectral Graph Clustering", IEEE ICASSP 2017