Attributed Network Embedding for Learning in a Dynamic Environment

Abstract

Network embedding leverages the node proximity manifested to learn a low-dimensional node vector representation for each node in the network. The learned embeddings could advance various learning tasks such as node classification, network clustering, and link prediction. Most, if not all, of the existing works, are overwhelmingly performed in the context of plain and static networks. Nonetheless, in reality, network structure often evolves over time with addition/deletion of links and nodes. Also, a vast majority of real-world networks are associated with a rich set of node attributes, and their attribute values are also naturally changing, with the emerging of new content patterns and the fading of old content patterns. These changing characteristics motivate us to seek an effective embedding representation to capture network and attribute evolving patterns, which is of fundamental importance for learning in a dynamic environment. To our best knowledge, we are the first to tackle this problem with the following two challenges: (1) the inherently correlated network and node attributes could be noisy and incomplete, it necessitates a robust consensus representation to capture their individual properties and correlations; (2) the embedding learning needs to be performed in an online fashion to adapt to the changes accordingly. In this paper, we tackle this problem by proposing a novel dynamic attributed network embedding framework - DANE. In particular, DANE first provides an offline method for a consensus embedding and then leverages matrix perturbation theory to maintain the freshness of the end embedding results in an online manner. We perform extensive experiments on both synthetic and real attributed networks to corroborate the effectiveness and efficiency of the proposed framework.

10 pages

References in corpus (6)

• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Homophily and Contagion Are Generically Confounded in Observational Social Network Studies
• A Survey on Multi-view Learning
• Node Classification in Social Networks
• User-level sentiment analysis incorporating social networks

Cited by in corpus (61)

• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
• Learning Graph Embedding with Adversarial Training Methods
• Streaming Graph Neural Networks via Continual Learning
• TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
• Efficiently Embedding Dynamic Knowledge Graphs
• Representation Learning for Dynamic Graphs: A Survey
• GloDyNE: Global Topology Preserving Dynamic Network Embedding
• Network Representation Learning: A Survey
• Recommender systems based on graph embedding techniques: A comprehensive review
• Dynamic Graph Convolutional Networks Using the Tensor M-Product
• Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
• DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph
• A Survey on Dynamic Network Embedding
• HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding
• Federated Dynamic GNN with Secure Aggregation
• Efficient Representation Learning Using Random Walks for Dynamic Graphs
• Unsupervised Attributed Multiplex Network Embedding
• Learning Dynamic Embeddings from Temporal Interactions
• AliGraph: A Comprehensive Graph Neural Network Platform
• Deep Representation Learning for Social Network Analysis
• Recommending on graphs: a comprehensive review from a data perspective
• Deep Graph Similarity Learning: A Survey
• Understanding graph embedding methods and their applications
• Embedding and trajectories of temporal networks
• DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
• TIMERS: Error-Bounded SVD Restart on Dynamic Networks
• Network Embedding via Deep Prediction Model
• SPINE: Structural Identity Preserved Inductive Network Embedding
• Dynamic Node Embeddings from Edge Streams
• EPNE: Evolutionary Pattern Preserving Network Embedding
• ANAE: Learning Node Context Representation for Attributed Network Embedding
• EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs
• Billion-scale Network Embedding with Iterative Random Projection
• Learning Vertex Representations for Bipartite Networks
• EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection
• Feature Interaction-aware Graph Neural Networks
• Accelerating Dynamic Network Embedding with Billions of Parameter Updates to Milliseconds
• GRADE: Graph Dynamic Embedding
• Multi-Level Network Embedding with Boosted Low-Rank Matrix Approximation
• Semantic Graph Neural Network with Multi-measure Learning for Semi-supervised Classification
• Graph Embedding Based Hybrid Social Recommendation System
• On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs
• The Atlas for the Aspiring Network Scientist
• USTAR: Online Multimodal Embedding for Modeling User-Guided Spatiotemporal Activity
• From Static to Dynamic Node Embeddings
• Dynamic Graph Collaborative Filtering
• ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding
• A Frequency-Structure Approach for Link Stream Analysis
• Temporal Network Embedding with Micro- and Macro-dynamics
• Robust Dynamic Network Embedding via Ensembles
• ConvDySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention and Convolutional Neural Networks
• struc2gauss: Structural Role Preserving Network Embedding via Gaussian Embedding
• Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling
• Dynamic Embedding on Textual Networks via a Gaussian Process
• FI-GRL: Fast Inductive Graph Representation Learning via Projection-Cost Preservation
• Multi-View Dynamic Heterogeneous Information Network Embedding
• Embedding Dynamic Attributed Networks by Modeling the Evolution Processes
• Fast Generating A Large Number of Gumbel-Max Variables
• cube2net: Efficient Query-Specific Network Construction with Data Cube Organization
• FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding
• NEMR: Network Embedding on Metric of Relation