DeepWalk

2014/03/26 by Bryan Perozzi, Rami Al-Rfou, Steven Skiena · 2 voices · 115 citations
Computer Science · #Topic Modeling #Advanced Graph Neural Networks #Natural Language Processing Techniques

paper · pdf · doi:10.1145/2623330.2623732

Abstract

We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily exploited by statistical models. DeepWalk generalizes recent advancements in language modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs.

Citations

• ImageNet classification with deep convolutional neural networks

Cited by

• A Comprehensive Survey on Graph Neural Networks
• Plausibility-Driven Prioritization of Candidate Biomedical Annotations
• Selectivity Matters: Source Node Influence Pruning for Unsupervised Graph Domain Adaptation
• Automated Reinforcement Learning: An Overview
• ECHO: Encoding Communities via High-order Operators
• A Survey on <scp>GNN</scp> ‐Based Link Prediction: Techniques, Applications, and Challenges
• Multilayer network science: theory, methods, and applications
• Technology fusion forecasting research via temporal hypergraph link prediction
• Domain matters: Towards domain-informed evaluation for link prediction
• Community Interaction and Conflict on the Web
• Multi-Head Spectral-Adaptive Graph Anomaly Detection
• Code for: Uncovering simultaneous breakthroughs with a robust measure of disruptiveness
• Unsupervised Graph Representation Learning with Complementary View Alignment
• TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation
• Semantic Refinement with LLMs for Graph Representations
• Entropic trade-off relations in stochastic thermodynamics via replica Markov processes
• Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
• ScamSweeper: Detecting Illegal Accounts in Web3 Scams via Transactions Analysis
• ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs
• Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation
• A Survey on Hypergraph Representation Learning
• Attacking and Securing Community Detection: A Game-Theoretic Framework
• Representation of the structure of graphs by sequences of instructions
• Restoring Network Evolution from Static Structure
• Graph contrastive learning with implicit augmentations
• Learning-based Link Prediction Methods Integrating Network Topological Features and Embedding Representations
• Bypassing Skip-Gram Negative Sampling: Dimension Regularization as a More Efficient Alternative for Graph Embeddings
• Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
• Embedding networks with the random walk first return time distribution
• Layered Division and Global Allocation for Community Detection in Multilayer Network
• A Literature Review of Recent Graph Embedding Techniques for Biomedical Data
• FlexiWalker: Extensible GPU Framework for Efficient Dynamic Random Walks with Runtime Adaptation
• Accumulated Local Effects and Graph Neural Networks for link prediction
• Graph Neural Networks for Vehicular Social Networks: Trends, Challenges, and Opportunities
• Hierarchical Frequency-Decomposition Graph Neural Networks for Road Network Representation Learning
• Heterogeneous Graph Neural Networks for Assumption-Based Argumentation
• HiLoMix: Robust High- and Low-Frequency Graph Learning Framework for Mixing Address Association
• On Stealing Graph Neural Network Models
• Dual-branch Spatial-Temporal Self-supervised Representation for Enhanced Road Network Learning
• Learning Time-Varying Graph Signals via Koopman
• Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms
• G2rammar: Bilingual Grammar Modeling for Enhanced Text-attributed Graph Learning
• Spectral Neural Graph Sparsification
• Aeolus: A Multi-structural Flight Delay Dataset
• Self-supervised Learning: Generative or Contrastive
• Geometric Deep Learning: Going beyond Euclidean data
• A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions
• Towards Effective Author Name Disambiguation by Hybrid Attention
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Predicting electric vehicle charging demand using a heterogeneous spatio-temporal graph convolutional network
• Random Search Neural Networks for Efficient and Expressive Graph Learning
• Drug-disease networks and drug repurposing
• Deep AI military staff: cooperative battlefield situation awareness for commander’s decision making
• Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
• Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphs
• Networks Multiscale Entropy Analysis
• FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization
• Preference-driven Knowledge Distillation for Few-shot Node Classification
• Open Biomedical Network Benchmark A Python Toolkit for Benchmarking Datasets with Biomedical Networks
• Hybrid Quantum-Classical Walks for Graph Representation Learning in Community Detection
• Inductive inference of gradient-boosted decision trees on graphs for insurance fraud detection
• Diffusion-Assisted Distillation for Self-Supervised Graph Representation Learning with MLPs
• From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning
• Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
• Graph2Region: Efficient Graph Similarity Learning with Structure and Scale Restoration
• NeuSO: Neural Optimizer for Subgraph Queries
• Node Classification via Simplicial Interaction with Augmented Maximal Clique Selection
• Hybrid Graph Embeddings and Louvain Algorithm for Unsupervised Community Detection
• RNE: computing shortest paths using road network embedding
• Deep learning in-depth analysis of crystal graph convolutional neural networks: A new era in materials discovery and its applications
• Account credibility inference based on news-sharing networks
• Exploring Heterophily in Graph-level Tasks
• Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs
• Word2VecGD: Neural Graph Drawing with Cosine-Stress Optimization
• Effective Clustering for Large Multi-Relational Graphs
• State Space Models over Directed Graphs
• Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering
• Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis
• No Community Detection Method to Rule Them All!
• Event2Vec: A Geometric Approach to Learning Composable Representations of Event Sequences
• Information Loss and Disparate Effects in Network Embeddings
• Representation Learning on Large Non-Bipartite Transaction Networks using GraphSAGE
• Network Embedding Analysis for Anti-Money Laundering Detection
• The Role of Community Detection Methods in Performance Variations of Graph Mining Tasks
• Influence Maximization Considering Influence, Cost and Time
• Label-Aware Graph Convolutional Networks
• MSRFormer: Road Network Representation Learning using Multi-scale Feature Fusion of Heterogeneous Spatial Interactions
• LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embedding
• VulRTex: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report
• KGBERT4Eth: A Feature-Complete Transformer Powered by Knowledge Graph for Multi-Task Ethereum Fraud Detection
• From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walks
• HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
• Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchies
• An Efficient Hybridization of Graph Representation Learning and Metaheuristics for the Constrained Incremental Graph Drawing Problem
• Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting
• OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations
• A statistical test for network similarity
• SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
• Multimodal Data Storage and Retrieval for Embodied AI: A Survey
• Heterogeneous Influence Maximization in User Recommendation
• Conformal Prediction for Network-Assisted Regression
• Contrastive Multi-View Graph Hashing
• Towards the Next-generation Bayesian Network Classifiers
• Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation
• Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
• GRAVITY: A Controversial Graph Representation Learning for Vertex Classification
• An Attention-based Graph Neural Network for Heterogeneous Structural Learning
• Recovering link-weight structure in complex networks with weight-aware random walks
• Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
• Hypergraph Neural Network with State Space Models for Node Classification
• DyCAF-Net: Dynamic Class-Aware Fusion Network
• MalFlows: Context-aware Fusion of Heterogeneous Flow Semantics for Android Malware Detection
• Graph Embedding in the Graph Fractional Fourier Transform Domain
• HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
• LLMs Between the Nodes: Community Discovery Beyond Vectors

Discussions

• DeepWalk: Online Learning of Social Representations [hn, 39 points, 6 comments]
• DeepWalk論文を読んだ。これって、ランダムウォークをつかって対象nodeが出現するsequenceをつくってそのノードの特徴量を得る上に、独立だからwalkerを複数走らせて並列化できる手法なのか。頭いいな。 arxiv.org/abs/1403.6652 [bsky, 0 points, 0 comments]

Related

• Comprehend DeepWalk as Matrix Factorization
• Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings
• Network Representation Learning: From Traditional Feature Learning to Deep Learning
• Representation Learning on Graphs with Jumping Knowledge Networks
• Graph Neural Networks: Methods, Applications, and Opportunities