Community Detection Based on Graph Representation Learning in Evolutionary Networks

Aiming at analyzing the temporal structures in evolutionary networks, we propose a community detection algorithm based on graph representation learning. The proposed algorithm employs a Laplacian matrix to obtain the node relationship information of the directly connected edges of the network structure at the previous time slice, the deep sparse autoencoder learns to represent the network structure under the current time slice, and the K-means clustering algorithm is used to partition the low-dimensional feature matrix of the network structure under the current time slice into communities. Experiments on three real datasets show that the proposed algorithm outperformed the baselines regarding effectiveness and feasibility.

[1]  L.-E. Martinet,et al.  Robust dynamic community detection with applications to human brain functional networks , 2020, Nature Communications.

[2]  P. Rousseeuw Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[3]  Peng Zhang,et al.  Nonlinear Dimensionality Reduction by Locally Linear Inlaying , 2009, IEEE Transactions on Neural Networks.

[4]  Tao Ren,et al.  A survey of community detection methods in multilayer networks , 2020, Data Mining and Knowledge Discovery.

[5]  Rui Ding,et al.  Detecting the urban traffic network structure dynamics through the growth and analysis of multi-layer networks , 2018, Physica A: Statistical Mechanics and its Applications.

[6]  Ravi Kumar,et al.  Structure and evolution of online social networks , 2006, KDD '06.

[7]  Keith C. C. Chan,et al.  Learning Latent Factors for Community Identification and Summarization , 2018, IEEE Access.

[8]  Y. Lai,et al.  Remote control of cascading dynamics on complex multilayer networks , 2019, New Journal of Physics.

[9]  Wei Jie,et al.  Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory , 2021, Inf..

[10]  Samee Ullah Khan,et al.  Analysis of Online Social Network Connections for Identification of Influential Users , 2018, ACM Comput. Surv..

[11]  KumarRavi,et al.  On the Bursty Evolution of Blogspace , 2005 .

[12]  Yasser Iturria-Medina,et al.  A method for multiscale community detection in brain networks , 2019, bioRxiv.

[13]  Bo Hu,et al.  Dynamic Network Community Detection With Coherent Neighborhood Propinquity , 2020, IEEE Access.

[14]  A. Z. M. Ehtesham Chowdhury,et al.  Community Detection in Social Network using Temporal Data , 2019, ArXiv.

[15]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[16]  Jing Yang,et al.  Dynamic Community Recognition Algorithm Based on Node Embedding and Linear Clustering , 2020 .

[17]  Michael C. Hout,et al.  Multidimensional Scaling , 2003, Encyclopedic Dictionary of Archaeology.

[18]  Yasser Iturria-Medina,et al.  Detecting brain network communities: considering the role of information flow and its different temporal scales , 2020 .

[19]  J. Kurths,et al.  Dynamic community discovery via common subspace projection , 2021, New Journal of Physics.

[20]  Srinivasan Parthasarathy,et al.  An event-based framework for characterizing the evolutionary behavior of interaction graphs , 2007, KDD '07.

[21]  Xuelong Li,et al.  Evolutionary Markov Dynamics for Network Community Detection , 2022, IEEE Transactions on Knowledge and Data Engineering.

[22]  Bernhard Schölkopf,et al.  Uncovering the Temporal Dynamics of Diffusion Networks , 2011, ICML.

[23]  Masoud Barati,et al.  C-Blondel: An Efficient Louvain-Based Dynamic Community Detection Algorithm , 2020, IEEE Transactions on Computational Social Systems.

[24]  Jing Liu,et al.  Evolutionary Network Embedding Preserving Both Local Proximity and Community Structure , 2020, IEEE Transactions on Evolutionary Computation.

[25]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[26]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.