struc2vec: Learning Node Representations from Structural Identity

Abstract

Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning techniques. This work presents struc2vec, a novel and flexible framework for learning latent representations for the structural identity of nodes. struc2vec uses a hierarchy to measure node similarity at different scales, and constructs a multilayer graph to encode structural similarities and generate structural context for nodes. Numerical experiments indicate that state-of-the-art techniques for learning node representations fail in capturing stronger notions of structural identity, while struc2vec exhibits much superior performance in this task, as it overcomes limitations of prior approaches. As a consequence, numerical experiments indicate that struc2vec improves performance on classification tasks that depend more on structural identity.

arXiv comment10 pages, KDD2017, Research Track

References in corpus (6)

• Efficient Estimation of Word Representations in Vector Space
• DeepWalk: Online Learning of Social Representations
• Cooperative Game Theory Approaches for Network Partitioning
• LINE: Large-scale Information Network Embedding
• Vertex similarity in networks
• subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs

Cited by in corpus (191)

• Self-supervised Learning: Generative or Contrastive
• Graph Contrastive Learning with Augmentations
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• Deep Graph Contrastive Representation Learning
• Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
• Learning Structural Node Embeddings Via Diffusion Wavelets
• Contrastive Multi-View Representation Learning on Graphs
• A Gentle Introduction to Deep Learning for Graphs
• VERSE: Versatile Graph Embeddings from Similarity Measures
• Link Prediction Based on Graph Neural Networks
• REGAL: Representation Learning-based Graph Alignment
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets
• A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
• NetLSD: Hearing the Shape of a Graph
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks
• Geom-GCN: Geometric Graph Convolutional Networks
• Behavior-aware Account De-anonymization on Ethereum Interaction Graph
• Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts
• Network Together: Node Classification via Cross network Deep Network Embedding
• Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
• K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
• Measuring and Improving the Use of Graph Information in Graph Neural Networks
• Learning Role-based Graph Embeddings
• Single Node Injection Attack against Graph Neural Networks
• MODEL: Motif-based Deep Feature Learning for Link Prediction
• GEMSEC: Graph Embedding with Self Clustering
• A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization
• Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
• mvn2vec: Preservation and Collaboration in Multi-View Network Embedding
• CONE-Align: Consistent Network Alignment with Proximity-Preserving Node Embedding
• tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
• Network Representation Learning: A Survey
• Multi-Task Representation Learning with Multi-View Graph Convolutional Networks
• Recommender systems based on graph embedding techniques: A comprehensive review
• Human Values and Attitudes towards Vaccination in Social Media
• FREDE: Anytime Graph Embeddings
• Altruistic and Profit-oriented: Making Sense of Roles in Web3 Community from Airdrop Perspective
• Graph Mining for Cybersecurity: A Survey
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Propositionalization and Embeddings: Two Sides of the Same Coin
• Network representation learning systematic review: ancestors and current development state
• Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
• Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
• Non-Local Graph Neural Networks
• Binarized Graph Neural Network
• Embedding-based Silhouette Community Detection
• Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
• G-CREWE: Graph CompREssion With Embedding for Network Alignment
• Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?
• On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network
• CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning
• Network Embedding: An Overview
• Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
• Conditional Network Embeddings
• Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily
• GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning
• Unsupervised Attributed Multiplex Network Embedding
• HONEM: Learning Embedding for Higher Order Networks
• Link Prediction via Graph Attention Network
• Cross-domain Network Representations
• Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices
• Approximation Ratios of Graph Neural Networks for Combinatorial Problems
• Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework
• AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks
• AliGraph: A Comprehensive Graph Neural Network Platform
• DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification
• Deep Adversarial Network Alignment
• Source Free Unsupervised Graph Domain Adaptation
• HONE: Higher-Order Network Embeddings
• Embedding Node Structural Role Identity into Hyperbolic Space
• CasGCN: Predicting future cascade growth based on information diffusion graph
• Network Classification in Temporal Networks Using Motifs
• Advancing Biomedicine with Graph Representation Learning: Recent Progress, Challenges, and Future Directions
• client2vec: Towards Systematic Baselines for Banking Applications
• Zoo Guide to Network Embedding
• Network Representation Learning: Consolidation and Renewed Bearing
• On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
• DeepTrax: Embedding Graphs of Financial Transactions
• SSNE: Effective Node Representation for Link Prediction in Sparse Networks
• Graphlets versus node2vec and struc2vec in the task of network alignment
• Graph Representation Learning for Popularity Prediction Problem: A Survey
• Outlier Aware Network Embedding for Attributed Networks
• Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
• Network Embedding via Deep Prediction Model
• RoleSeer: Understanding Informal Social Role Changes in MMORPGs via Visual Analytics
• Dynamic Node Embeddings from Edge Streams
• SPINE: Structural Identity Preserved Inductive Network Embedding
• RiWalk: Fast Structural Node Embedding via Role Identification
• QUINT: Node embedding using network hashing
• Deep Node Ranking for Neuro-symbolic Structural Node Embedding and Classification
• Dynamic Network Embeddings for Network Evolution Analysis
• Beyond Node Embedding: A Direct Unsupervised Edge Representation Framework for Homogeneous Networks
• ANAE: Learning Node Context Representation for Attributed Network Embedding
• Embedding Node Structural Role Identity Using Stress Majorization
• Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
• Calibrating and Improving Graph Contrastive Learning
• SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks
• Topic-aware latent models for representation learning on networks
• Latent Network Summarization: Bridging Network Embedding and Summarization
• Graph-based Village Level Poverty Identification
• Billion-scale Network Embedding with Iterative Random Projection
• Price graphs: Utilizing the structural information of financial time series for stock prediction
• GCN-SL: Graph Convolutional Networks with Structure Learning for Graphs under Heterophily
• Representation Learning on Graphs: A Reinforcement Learning Application
• Relation Structure-Aware Heterogeneous Information Network Embedding
• Semi-Supervised Learning on Graphs Based on Local Label Distributions
• Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank
• EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection
• Combating the Filter Bubble: Designing for Serendipity in a University Course Recommendation System
• Preserving Local and Global Information for Network Embedding
• Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness
• Time-Series Snapshot Network for Partner Recommendation: A Case Study on OSS
• The Importance of Being Correlated: Implications of Dependence in Joint Spectral Inference across Multiple Networks
• Integrating Network Embedding and Community Outlier Detection via Multiclass Graph Description
• A Unified Framework for Community Detection and Network Representation Learning
• Flexible Attributed Network Embedding
• Hyperbolic Neural Collaborative Recommender
• An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
• Hypergraph Neural Network with State Space Models for Node Classification
• Less is More: Simple yet Effective Heuristic Community Detection with Graph Convolution Network
• Improving link prediction accuracy of network embedding algorithms via rich node attribute information
• The Atlas for the Aspiring Network Scientist
• Dynamic Link Prediction Using Graph Representation Learning with Enhanced Structure and Temporal Information
• PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
• GraLSP: Graph Neural Networks with Local Structural Patterns
• GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks
• Runtime Analysis of Whole-System Provenance
• GraphMI: Extracting Private Graph Data from Graph Neural Networks
• From Static to Dynamic Node Embeddings
• Diffusion Based Network Embedding
• Message Passing Graph Kernels
• Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks
• Graph-Level Embedding for Time-Evolving Graphs
• A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
• SepNE: Bringing Separability to Network Embedding
• MLANE: Meta-Learning Based Adaptive Network Embedding
• struc2gauss: Structural Role Preserving Network Embedding via Gaussian Embedding
• Feature Correlation Aggregation: on the Path to Better Graph Neural Networks
• Dynamic Graph Embedding via LSTM History Tracking
• Block-Approximated Exponential Random Graphs
• Graph Operator Modeling over Large Graph Datasets
• Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning
• Inductive Graph Embeddings through Locality Encodings
• Learning Features of Network Structures Using Graphlets
• Lorentzian Graph Convolutional Networks
• Provenance Graph Kernel
• Utilizing Citation Network Structure to Predict Citation Counts: A Deep Learning Approach
• Learning Conjoint Attentions for Graph Neural Nets
• Self-Supervised Deep Graph Embedding with High-Order Information Fusion for Community Discovery
• Inferential SIR-GN: Scalable Graph Representation Learning
• AHINE: Adaptive Heterogeneous Information Network Embedding
• Network2Vec Learning Node Representation Based on Space Mapping in Networks
• Predicting Critical Nodes in Temporal Networks by Dynamic Graph Convolutional Networks
• Towards Self-Explainable Graph Neural Network
• Automated Feature-Topic Pairing: Aligning Semantic and Embedding Spaces in Spatial Representation Learning
• Link prediction on multi-relational graphs from an influence propagation perspective
• RUM: network Representation learning throUgh Multi-level structural information preservation
• QMUL-SDS @ SardiStance: Leveraging Network Interactions to Boost Performance on Stance Detection using Knowledge Graphs
• Toward Edge-Centric Network Embeddings
• Vulcan: Solving the Steiner Tree Problem with Graph Neural Networks and Deep Reinforcement Learning
• Role Similarity Metric Based on Spanning Rooted Forest
• Barlow Graph Auto-Encoder for Unsupervised Network Embedding
• Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization
• Variational Embeddings for Community Detection and Node Representation
• Fast Approximate Solutions using Reinforcement Learning for Dynamic Capacitated Vehicle Routing with Time Windows
• MultiWalk: A Framework to Generate Node Embeddings Based on an Ensemble of Walk Methods
• Joint Use of Node Attributes and Proximity for Semi-Supervised Classification on Graphs
• Modeling Heterogeneous Edges to Represent Networks with Graph Auto-Encoder
• Graph Structural-topic Neural Network
• Learning Heat Diffusion for Network Alignment
• Exemplar-based Layout Fine-tuning for Node-link Diagrams
• Prob2Vec: Mathematical Semantic Embedding for Problem Retrieval in Adaptive Tutoring
• A Block-based Generative Model for Attributed Networks Embedding
• Constrained Non-Affine Alignment of Embeddings
• A characterization of 2-neighborhood degree list of diameter 2 graphs
• Tutorial on NLP-Inspired Network Embedding
• Differentially Private Link Prediction With Protected Connections
• A Survey on Role-Oriented Network Embedding
• Multi-Hot Compact Network Embedding
• cube2net: Efficient Query-Specific Network Construction with Data Cube Organization
• Representation Learning by Reconstructing Neighborhoods
• FinBrain: When Finance Meets AI 2.0
• Using Distributional Thesaurus Embedding for Co-hyponymy Detection
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast