NetGAN: Generating Graphs via Random Walks

We propose NetGAN - the first implicit generative model for graphs able to mimic real-world networks. We pose the problem of graph generation as learning the distribution of biased random walks over the input graph. The proposed model is based on a stochastic neural network that generates discrete output samples and is trained using the Wasserstein GAN objective. NetGAN is able to produce graphs that exhibit the well-known network patterns without explicitly specifying them in the model definition. At the same time, our model exhibits strong generalization properties, as highlighted by its competitive link prediction performance, despite not being trained specifically for this task. Being the first approach to combine both of these desirable properties, NetGAN opens exciting further avenues for research.

• Publication year

  2018

• Venue

  International Conference on Machine Learning

• Publication date

  2018-03-02

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1803.00816
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• GENERATIVE ADVERSARIAL NETS

  2018cited by this paper
• Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure

  2018cited by this paper
• Scale-free networks are rare

  2018cited by this paper
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

  2017cited by this paper
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks

  2017cited by this paper
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets

  2017cited by this paper
• Adversarial Learning for Neural Dialogue Generation

  2017cited by this paper
• Can GAN Learn Topological Features of a Graph?

  2017cited by this paper
• Generating Multi-label Discrete Electronic Health Records using Generative Adversarial Networks

  2017cited by this paper
• Improved Training of Wasserstein GANs

  2017cited by this paper
• Boundary-Seeking Generative Adversarial Networks

  2017cited by this paper
• Learning Social Graph Topologies using Generative Adversarial Neural Networks

  2017cited by this paper
• Progressive Growing of GANs for Improved Quality, Stability, and Variation

  2017cited by this paper
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking

  2017cited by this paper
• Recurrent Topic-Transition GAN for Visual Paragraph Generation

  2017cited by this paper
• BEGAN: Boundary Equilibrium Generative Adversarial Networks

  2017cited by this paper
• Variational Graph Auto-Encoders

  2016influential reference
• Tri-Party Deep Network Representation

  2016cited by this paper
• Categorical Reparameterization with Gumbel-Softmax

  2016cited by this paper
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

  2016cited by this paper
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

  2016cited by this paper
• NIPS 2016 Tutorial: Generative Adversarial Networks

  2016cited by this paper
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution

  2016cited by this paper
• Structural Diversity and Homophily: A Study Across More Than One Hundred Big Networks

  2016cited by this paper
• node2vec: Scalable Feature Learning for Networks

  2016cited by this paper
• Multimedia Retrieval

  2014cited by this paper
• The graph-tool python library

  2014cited by this paper
• DeepWalk: online learning of social representations

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014influential reference
• Community structure and scale-free collections of Erdös-Rényi graphs

  2011influential reference
• Modeling Social Networks with Node Attributes using the Multiplicative Attribute Graph Model

  2011cited by this paper
• Stochastic blockmodels and community structure in networks

  2010influential reference
• A Survey of Statistical Network Models

  2009cited by this paper
• Collective Classification in Network Data

  2008cited by this paper
• Graph mining: Laws, generators, and algorithms

  2006cited by this paper
• The political blogosphere and the 2004 U.S. election: divided they blog

  2005cited by this paper
• Friends and neighbors on the Web

  2003cited by this paper
• Automating the Construction of Internet Portals with Machine Learning

  2000cited by this paper
• Emergence of Scaling in Random Networks

  1999cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• A Critical Point for Random Graphs with a Given Degree Sequence

  1995cited by this paper
• An Exponential Family of Probability Distributions for Directed Graphs

  1981influential reference
• The Asymptotic Number of Labeled Graphs with Given Degree Sequences

  1978cited by this paper
• Emergence of Scaling in Random Networks

  year unknowncited by this paper

• Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

  2026cites this paper
• GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures

  2026cites this paper
• Graph diffusion models: A comprehensive survey of methods and applications

  2026cites this paper
• Research on a Method for Generating 3D Topologies of Combat Networks Based on Conditional Graph Diffusion Models

  2026cites this paper
• Graph Neural Network (GNN) and its Application: A State-of-the-Art Survey

  2025cites this paper
• PrivDPR: Synthetic Graph Publishing with Deep PageRank under Differential Privacy

  2025cites this paper
• A Diffusive Data Augmentation Framework for Reconstruction of Complex Network Evolutionary History

  2025cites this paper
• A Comparative Study of GNNs and Rule-Based Methods for Synthetic Social Network Generation

  2025cites this paper
• Generative AI in depth: A survey of recent advances, model variants, and real-world applications

  2025cites this paper
• RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction

  2025cites this paper
• Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs

  2025cites this paper
• Differentially Private Diffusion Model for Graph Generation

  2025cites this paper
• CaRoLS: Condition-adaptive multi-level road layout synthesis

  2025cites this paper
• DPBRW-GGAN: Graph data generation based on biased random walk with differential privacy

  2025cites this paper
• AIGC for Graphs: Current Techniques and Future Trends

  2025cites this paper
• Generating Large Semi-Synthetic Graphs of Any Size

  2025cites this paper
• A Complex Network Model for Knowledge Graphs' Relationships

  2025influential citation
• Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs

  2025cites this paper
• Graph Neural Networks and Fault Tree Analysis for Runtime Dynamic Risk Assessment of Autonomous Systems

  2025cites this paper
• Flatten Graphs as Sequences: Transformers are Scalable Graph Generators

  2025cites this paper
• CONTINUUM: Detecting APT Attacks through Spatial-Temporal Graph Neural Networks

  2025cites this paper
• Sat2Flow: A Structure-Aware Diffusion Framework for Human Flow Generation from Satellite Imagery

  2025cites this paper
• Understanding and Mitigating Vulnerabilities of Random Walks against Adversarial Attacks

  2025cites this paper
• STGS: Spatio-temporal Graph Sparsification Using Reinforcement Learning

  2025cites this paper
• A Hybrid Approach for Threat Detection in Social Networks Using Graph Metrics and GANs

  2025cites this paper
• MINTT: Memory Inductive Transfer for Temporal Graph Neural Networks

  2025cites this paper
• BikeVAE-GNN: A Variational Autoencoder-Augmented Hybrid Graph Neural Network for Sparse Bicycle Volume Estimation

  2025cites this paper
• Deep generative models in energy system applications: Review, challenges, and future directions

  2025cites this paper
• Combining Graph Neural Networks and Mixed Integer Linear Programming for Molecular Inference under the Two-Layered Model

  2025cites this paper
• Attributed Hypergraph Generation with Realistic Interplay Between Structure and Attributes

  2025cites this paper
• PolyGraph Discrepancy: a classifier-based metric for graph generation

  2025cites this paper
• Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures

  2025cites this paper
• Scalable Learning-Based Community-Preserving Graph Generation

  2025influential citation
• GraphWeave : Interpretable and Robust Graph Generation via Random Walk Trajectories

  2025cites this paper
• Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities

  2025cites this paper
• Efficient Learning-Based Graph Simulation for Temporal Graphs

  2025influential citation
• A Feedback-Enhanced Graph Generative Model With Tunable Features

  2025cites this paper
• GI-Graph: A Generative Invariant Graph Learning Scheme Towards Out-of-Distribution Generalization

  2025cites this paper
• Generalized Personalized PageRank with Graph Convolutional Networks in Recommender Systems

  2025cites this paper
• Quantifying Heterogeneity of Complex Networks Based on Gintropy and Gini Indices

  2025cites this paper
• EDCM-EA: event prediction based on event development context mining considering event arguments

  2025cites this paper
• Probabilistic Graph Circuits: Deep Generative Models for Tractable Probabilistic Inference over Graphs

  2025cites this paper
• FG-SMOTE: Towards Fair Node Classification with Graph Neural Network

  2025cites this paper
• A Large-scale Benchmark Dataset for Commuting Origin-destination Matrix Generation

  2024cites this paper
• Want More WANs? Comparison of Traditional and GAN-Based Generation of Wide Area Network Topologies via Graph and Performance Metrics

  2024cites this paper
• Revealing an Overlooked Challenge in Class-Incremental Graph Learning

  2024cites this paper
• Generating sparse origin–destination flows on shared mobility networks using probabilistic graph neural networks

  2024cites this paper
• Efficient Dynamic Attributed Graph Generation

  2024cites this paper
• Variational Type Graph Autoencoder for Denoising on Event Recommendation

  2024cites this paper
• Heterogeneous Graph Generation: A Hierarchical Approach using Node Feature Pooling

  2024cites this paper
• Towards certifiable AI in aviation: landscape, challenges, and opportunities

  2024cites this paper
• PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities

  2024cites this paper
• CRTGAN: Controllable Road Network Graphs Generation via Transformer based GAN

  2024cites this paper
• Dual Adversarial Perturbators Generate rich Views for Recommendation

  2024cites this paper
• A review of graph neural networks and pretrained language models for knowledge graph reasoning

  2024cites this paper
• PROXI: Challenging the GNNs for Link Prediction

  2024cites this paper
• Generating-Based Attacks to Online Social Networks

  2024cites this paper
• Survey on Graph Neural Networks

  2024cites this paper
• Secure Causal Reasoning on Coarsened Graph for Privacy-aware Social Web Services

  2024cites this paper
• Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

  2024cites this paper
• Temporal Graph Generation Featuring Time-Bound Communities

  2024cites this paper
• Random Walk Diffusion for Efficient Large-Scale Graph Generation

  2024influential citation
• Learning probability distributions over georeferenced distribution grid models

  2024cites this paper
• RoBus: A Multimodal Dataset for Controllable Road Networks and Building Layouts Generation

  2024cites this paper
• Deep Reinforcement Learning for Adverse Garage Scenario Generation

  2024cites this paper
• An effective keyword search co-occurrence multi-layer graph mining approach

  2024cites this paper
• Complex Graph Analysis and Representation Learning: Problems, Techniques, and Applications

  2024cites this paper
• Quantifying uncertainty in graph neural network explanations

  2024cites this paper
• IGCN: A Provably Informative GCN Embedding for Semi-Supervised Learning With Extremely Limited Labels

  2024cites this paper
• CGGM: A conditional graph generation model with adaptive sparsity for node anomaly detection in IoT networks

  2024cites this paper
• A borehole clustering based method for lithological identification using logging data

  2024cites this paper
• SteinGen: Generating Fidelitous and Diverse Graph Samples

  2024influential citation
• Random-Based and Deep Graph Generators: Evolution and Future Prospects

  2024cites this paper
• Artificial Intelligence for Complex Network: Potential, Methodology and Application

  2024cites this paper
• Anomaly Detection using Generative Adversarial Networks Reviewing methodological progress and challenges

  2024cites this paper
• System Identification for Temporal Networks

  2024cites this paper
• Expected Probabilistic Hierarchies

  2024cites this paper
• Application of Generative Graph Models in Biological Network Regeneration: A Selective Review and Qualitative Analysis

  2024cites this paper
• Heterogeneous network-based algorithms in the biomedical data mining: A review from technical perspective

  2024cites this paper
• FairWire: Fair Graph Generation

  2024cites this paper
• A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation

  2024cites this paper
• Exploring Task Unification in Graph Representation Learning via Generative Approach

  2024cites this paper
• Efficient and Optimized Small Organic Molecular Graph Generation Pathway Using a Quantum Generative Adversarial Network

  2024cites this paper
• MOSS: A Large-scale Open Microscopic Traffic Simulation System

  2024cites this paper
• A Deep Learning Framework for Evaluating Dynamic Network Generative Models and Anomaly Detection

  2024cites this paper
• Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections

  2024cites this paper
• Graph Contrastive Learning with Adversarial Structure Refinement (GCL-ASR)

  2024cites this paper
• Graph Attention Based Variational Adversarial Graph Generation Method

  2023cites this paper
• Graph Contrastive Learning with Generative Adversarial Network

  2023cites this paper
• A Large Scale Synthetic Graph Dataset Generation Framework

  2023cites this paper
• NetRL: Task-Aware Network Denoising via Deep Reinforcement Learning

  2023cites this paper
• Unbiased Library of k-regular, n-sized, Connected, Small Graphs

  2023cites this paper
• Data Augmentation for Supervised Graph Outlier Detection via Latent Diffusion Models

  2023cites this paper
• GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generators

  2023cites this paper
• Holistic Prediction on a Time-Evolving Attributed Graph

  2023cites this paper
• RegraphGAN: A graph generative adversarial network model for dynamic network anomaly detection

  2023cites this paper
• Privacy-Preserved Evolutionary Graph Modeling via Gromov-Wasserstein Autoregression

  2023cites this paper
• TenGAN: adversarially generating multiplex tensor graphs

  2023cites this paper
• Improving an Electronic Health Record–Based Clinical Prediction Model Under Label Deficiency: Network-Based Generative Adversarial Semisupervised Approach

  2023cites this paper
• Complexity-aware Large Scale Origin-Destination Network Generation via Diffusion Model

  2023cites this paper