Network representation learning or embedding aims to project the network into a low-dimensional space that can be devoted to different network tasks. Temporal networks are an important type of network whose topological structure changes over time. Compared with methods on static networks, temporal network embedding (TNE) methods are facing three challenges: 1) it cannot describe the temporal dependence across network snapshots; 2) the node embedding in the latent space fails to indicate changes in the network topology; and 3) it cannot avoid a lot of redundant computation via parameter inheritance on a series of snapshots. To overcome these problems, we propose a novel TNE method named temporal network embedding method based on the VAE framework (TVAE), which is based on a variational autoencoder (VAE) to capture the evolution of temporal networks for link prediction. It not only generates low-dimensional embedding vectors for nodes but also preserves the dynamic nonlinear features of temporal networks. Through the combination of a self-attention mechanism and recurrent neural networks, TVAE can update node representations and keep the temporal dependence of vectors over time. We utilize parameter inheritance to keep the new embedding close to the previous one, rather than explicitly using regularization, and thus, it is effective for large-scale networks. We evaluate our model and several baselines on synthetic data sets and real-world networks. The experimental results demonstrate that TVAE has superior performance and lower time cost compared with the baselines.

Recently, Network Embedding (NE) has become one of the most attractive research topics in machine learning and data mining. NE approaches have achieved promising performance in various graph mining tasks including link prediction and node clustering and classification. A wide variety of NE methods focus on the proximity of networks, they learn community-oriented embedding for each node, where the corresponding representations are similar if two nodes are closer to each other in the network. Meanwhile, there is another type of structural similarity, i.e., role-based similarity, which is completely different from and complementary to the proximity. In order to preserve the role-based structural similarity, the problem of role-oriented NE is raised. However, compared to the community-oriented NE, there are only a few role-oriented embedding approaches proposed recently. Although less explored, considering the importance of roles in analyzing networks and many applications that role-oriented NE can shed light on, it is necessary and timely to provide a comprehensive overview of existing role-oriented NE methods. In this review, we first clarify the differences between community-oriented and role-oriented network embedding. Afterward, we propose a general framework for understanding role-oriented NE and a two-level categorization to better classify existing methods. Then, we select some representative methods according to the proposed categorization and briefly introduce them by discussing their motivation, development, and differences. Moreover, we conduct comprehensive experiments to empirically evaluate these methods on a variety of role-related tasks including node classification and clustering (role discovery), top-k similarity search, and visualization using some widely used synthetic and real-world datasets. Finally, we further discuss the research trend of role-oriented NE from the perspective of applications and point out some potential future directions.

Recently, network embedding (NE) is an amazing research point in complex networks and devoted to a variety of tasks. Nearly, all the methods and models of NE are based on the local, high-order, or global similarity of the networks, and few studies have focused on the role discovery or structural similarity, which is of great significance in spreading dynamics and network theory. Meanwhile, existing NE models for role discovery suffer from two limitations, that is: 1) they fail to model the varying dependencies between each node and its neighbor nodes and 2) they cannot capture the effective node features which are helpful to role discovery, which makes these methods ineffective when applied to the role discovery task. To solve the above problems of NE for role discovery or structural similarity, we propose a unified deep learning framework, called RDAA, which can effectively represent features of nodes and benefit the Role Discovery-guided NE with a deep autoencoder, while modeling the local links with an Attention mechanism. In addition, we design an elaborately binding technique to combine both parts and optimize the framework in a unified way. We conduct different experiments, including visualization, role classification, role discovery, and running time compared to popular NE methods for both proximity and structural similarity. The RDAA has better performance on all the datasets and achieves good tradeoffs.

Network Embedding (NE) is one of the most popular learning methods in complex networks. It aims at learning the low-dimensional representations of nodes in networks and has been applied in a variety of network analytic tasks. Most existing methods of NE are designed by merely using the local, high-order or global proximity to preserve the network structure; hence they are incapable of fully capturing the structural identity of nodes, which is a concept of symmetry defined by the network structure and their relationship to other nodes. There are two limitations to existing NE models. First, the local and global node dependency information is not considered simultaneously. Second, there is no adequate framework that can reveal the role property of each node. In this paper, we propose an intuitive and unified deep learning framework named DMER, short for Deep Mutual Encode for Embedding, to learn node embeddings from structural identity. In our model, Graph Convolution Network (GCN) is adopted to model the dependency relations between nodes from a global perspective. An Auto-Encoder (AE) framework is proposed to reconstruct the features of nodes, and it can conclusively reveal the structural identity from network structure. By integrating the GCN and AE components with a shared and constrained mechanism, the proposed model implements mutual enhancement for node embedding from structural identity. Experimental results based on structural role classification and visualization demonstrate that our model achieves better performance compared with the state-of-the-art methods.