Attributed Social Network Embedding

Abstract

Embedding network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification and entity retrieval. However, most existing methods focused only on leveraging network structure. For social networks, besides the network structure, there also exists rich information about social actors, such as user profiles of friendship networks and textual content of citation networks. These rich attribute information of social actors reveal the homophily effect, exerting huge impacts on the formation of social networks. In this paper, we explore the rich evidence source of attributes in social networks to improve network embedding. We propose a generic Social Network Embedding framework (SNE), which learns representations for social actors (i.e., nodes) by preserving both the structural proximity and attribute proximity. While the structural proximity captures the global network structure, the attribute proximity accounts for the homophily effect. To justify our proposal, we conduct extensive experiments on four real-world social networks. Compared to the state-of-the-art network embedding approaches, SNE can learn more informative representations, achieving substantial gains on the tasks of link prediction and node classification. Specifically, SNE significantly outperforms node2vec with an 8.2% relative improvement on the link prediction task, and a 12.7% gain on the node classification task.

arXiv comment12 pages, 7 figures

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Distributed Representations of Words and Phrases and their Compositionality
• DeepWalk: Online Learning of Social Representations
• Distributed Representations of Sentences and Documents
• LINE: Large-scale Information Network Embedding
• Mixed membership stochastic blockmodels
• Social Structure of Facebook Networks
• Bibliographic Analysis with the Citation Network Topic Model
• Latent Space Model for Multi-Modal Social Data

Cited by in corpus (48)

• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Learning Graph Embedding with Adversarial Training Methods
• Spam Review Detection with Graph Convolutional Networks
• MODEL: Motif-based Deep Feature Learning for Link Prediction
• MultiVERSE: a multiplex and multiplex-heterogeneous network embedding approach
• GloDyNE: Global Topology Preserving Dynamic Network Embedding
• Recommender systems based on graph embedding techniques: A comprehensive review
• Predicting Attributes of Nodes Using Network Structure
• Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
• CatGCN: Graph Convolutional Networks with Categorical Node Features
• Deep Collaborative Embedding for information cascade prediction
• On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network
• PANE: scalable and effective attributed network embedding
• ExEm: Expert Embedding using dominating set theory with deep learning approaches
• AliGraph: A Comprehensive Graph Neural Network Platform
• RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training
• Deep Representation Learning for Social Network Analysis
• AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks
• Fast Matrix Factorization with Non-Uniform Weights on Missing Data
• Dynamic Node Embeddings from Edge Streams
• Attributed Network Embedding for Incomplete Attributed Networks
• ANAE: Learning Node Context Representation for Attributed Network Embedding
• QUINT: Node embedding using network hashing
• Learning Vertex Representations for Bipartite Networks
• Multi-Label Graph Convolutional Network Representation Learning
• Flexible Attributed Network Embedding
• EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection
• Attributed Network Embedding via Subspace Discovery
• Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
• On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs
• On the Structural Properties of Social Networks and their Measurement-calibrated Synthetic Counterparts
• The Atlas for the Aspiring Network Scientist
• Deep Dual Support Vector Data Description for Anomaly Detection on Attributed Networks
• Cyclic Label Propagation for Graph Semi-supervised Learning
• Representation Learning in Heterogeneous Professional Social Networks with Ambiguous Social Connections
• Multimodal Deep Network Embedding with Integrated Structure and Attribute Information
• Addressing Time Bias in Bipartite Graph Ranking for Important Node Identification
• HEAT: Hyperbolic Embedding of Attributed Networks
• GIPA: A General Information Propagation Algorithm for Graph Learning
• Learning-based link prediction analysis for Facebook100 network
• A Block-based Generative Model for Attributed Networks Embedding
• Will the Winner Take All? Competing Influences in Social Networks Under Information Overload
• Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks
• GAHNE: Graph-Aggregated Heterogeneous Network Embedding
• RUM: network Representation learning throUgh Multi-level structural information preservation
• Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks
• Label Embedding with Partial Heterogeneous Contexts