Community enhancement network embedding based on edge reweighting preprocessing

Abstract

Network embedding has attracted considerable attention in recent years. It represents nodes in a network into a low-dimensional vector space while keeping the properties of the network. Some methods (e.g. ComE, MNMF, and CARE) have been proposed to preserve the community property in network embedding, and they have obtained good results in some downstream network analysis tasks. However, there still exists a significant challenge because nodes may lose important structural information following embedding. To address this problem, we propose a community structure enhancement framework for network embedding, based on edge reweighting. Through edge reweighting, the weight of intra-community edges is increased while the weight of inter-community edges is decreased. Therefore, after embedding, nodes in the same community are closer to each other than nodes in different communities in the embedding space. We apply the edge reweighting as a preprocessing stage in network embedding, and construct an enhanced network by incorporating enhanced community structures into the original network. By doing this, the embedded vectors from the enhanced network can better perform all downstream network analysis tasks. Extensive experiments are conducted on two network analysis tasks (community detection and node classification) with synthetic and real-world datasets. The results show that our method outperforms state-of-the-art network embedding methods.

MERP: Motifs enhanced network embedding based on edge reweighting preprocessing

“…Network embedding, also known as network representation learning, maps the nodes in a network to vectors in a low-dimensional and dense space while preserving various structures and connectivity patterns between nodes [1,2]. These vectors can be used with existing machine learning algorithms to accomplish downstream network analysis tasks-e.g., node classification [3], link prediction [4], community detection [5], recommendation [6], and anomaly detection [7]. Due to the excellent performance in different network analysis tasks, network embedding has attracted a lot of attention.…”