Identification of dynamic networks community by fusing deep learning and evolutionary clustering

Abstract

Community detection is a critical component of network analysis and a hot topic in social computing. Detecting community structure in dynamic networks has important theoretical and practical implications for understanding the intrinsic function of networks and predicting network behavior. However, the majority of existing dynamic community detection methods adopt shallow models, which have limited ability to excavate complex non-linear structures and tend to generate undesirable community structures. In order to obtain an accurate and robust community structure in dynamic networks, we are inspired by network representation learning and utilize the deep learning to detect evolving communities in dynamic networks. In this paper, we propose a novel dynamic community detection method by fusing Deep Learning and Evolutionary Clustering (DLEC). This work attempts to combine deep learning and evolutionary clustering into a unified framework. First, we propose a matrix construction strategy to fully reveal the inherent community structures via the underlying community memberships. Then, we develop a novel multi-layer deep autoencoder framework that consists of multiple non-linear functions to extract the latent deep representation of the dynamic network. Based on the evolutionary clustering framework, a graph regularization term is introduced to ensure the smoothness of the community evolution. Finally, we employ the K-means clustering algorithm on the low-dimensional network space to obtain the community structure. Extensive experimental results on synthetic and real-world networks show that the proposed DLEC algorithm can effectively detect high-quality communities in dynamic networks.

Figure 1

The framework of DLEC.

Figure 2

The schematic diagram of network latent community structure.

Figure 3

Example of the network representation: adjacency matrix A and community similarity matrix X.

Figure 4

Example of using autoencoder for community detection in a snapshot.

Algorithm 1

DLEC: Identification of dynamic networks community by fusing deep learning and evolutionary clustering.

Figure 5

Comparison results of the algorithms on Synthetic Dataset 1 in terms of NMI. (A) SYN-FIX, zout = 3, (B) SYN-FIX, zout = 5.

Figure 6

Comparison results of the algorithms on Synthetic Dataset 1 in terms of NMI. (A) SYN-VAR, zout = 3, (B) SYN-VAR, zout = 5.

Figure 7

Comparison results of the algorithms on Synthetic Dataset 2 in terms of NMI. (A) zout = 5, C% = 10%, (B) zout = 5, C% = 30%.

Figure 8

Comparison results of the algorithms on Synthetic Dataset 2 in terms of NMI. (A) zout = 6, C% = 10%, (B) zout = 6, C% = 30%.

Figure 9

Comparison results of the algorithms on KIT-Email in terms of ER.

Figure 10

Comparison results of the algorithms on Enron email dataset in terms of NMI.

Figure 11

Visualization of community evolution of Enron email dataset at different times.

Figure 12

The community detection results over different $\alpha$ on datasets. (A) LNetwork1 dataset, (B) KIT-mail dataset.