Variational Graph Auto-Encoders

Abstract

We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model using a graph convolutional network (GCN) encoder and a simple inner product decoder. Our model achieves competitive results on a link prediction task in citation networks. In contrast to most existing models for unsupervised learning on graph-structured data and link prediction, our model can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.

Bayesian Deep Learning Workshop (NIPS 2016)

References in corpus (4)

• Scikit-learn: Machine Learning in Python
• Auto-Encoding Variational Bayes
• Semi-Supervised Classification with Graph Convolutional Networks
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Cited by in corpus (394)

• Inductive Representation Learning on Large Graphs
• An Introduction to Variational Autoencoders
• Graph Neural Networks: A Review of Methods and Applications
• Graph Neural Network for Traffic Forecasting: A Survey
• Fast Graph Representation Learning with PyTorch Geometric
• Graph Convolutional Matrix Completion
• Graph Contrastive Learning with Adaptive Augmentation
• Graph Contrastive Learning with Augmentations
• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Graph Self-Supervised Learning: A Survey
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Representation Learning for Attributed Multiplex Heterogeneous Network
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Deep Graph Contrastive Representation Learning
• Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
• Contrastive Multi-View Representation Learning on Graphs
• Learning Graph Embedding with Adversarial Training Methods
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• A Gentle Introduction to Deep Learning for Graphs
• Community detection in node-attributed social networks: a survey
• Link Prediction Based on Graph Neural Networks
• Hyperbolic Graph Convolutional Neural Networks
• An Overview of Deep Semi-Supervised Learning
• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
• Graph signal processing for machine learning: A review and new perspectives
• ETA Prediction with Graph Neural Networks in Google Maps
• NetGAN: Generating Graphs via Random Walks
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• Strategies for Pre-training Graph Neural Networks
• Molecular graph generation with Graph Neural Networks
• Design Space for Graph Neural Networks
• Deep Learning on Graphs: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• Signal Processing on Higher-Order Networks: Livin' on the Edge ... and Beyond
• Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• Learning on Attribute-Missing Graphs
• Graph Convolutional Networks for Graphs Containing Missing Features
• Graph Barlow Twins: A self-supervised representation learning framework for graphs
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• E(n) Equivariant Graph Neural Networks
• Consistent Multiple Graph Embedding for Multi-View Clustering
• Hyperspherical Variational Auto-Encoders
• Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
• Generative Models for Automatic Chemical Design
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Compositional Fairness Constraints for Graph Embeddings
• Graph Information Bottleneck
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Variational Graph Normalized Auto-Encoders
• Modeling Relational Data with Graph Convolutional Networks
• Putting An End to End-to-End: Gradient-Isolated Learning of Representations
• SATAR: A Self-supervised Approach to Twitter Account Representation Learning and its Application in Bot Detection
• Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification
• Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
• Measuring and Improving the Use of Graph Information in Graph Neural Networks
• GPT-GNN: Generative Pre-Training of Graph Neural Networks
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery
• Heterogeneous Deep Graph Infomax
• Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
• Semi-Implicit Graph Variational Auto-Encoders
• Explainability Techniques for Graph Convolutional Networks
• Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
• GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
• A Comparative Study for Unsupervised Network Representation Learning
• Graph Communal Contrastive Learning
• MultiVERSE: a multiplex and multiplex-heterogeneous network embedding approach
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• From Canonical Correlation Analysis to Self-supervised Graph Neural Networks
• Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
• Graph Structure Learning for Robust Graph Neural Networks
• BertGCN: Transductive Text Classification by Combining GCN and BERT
• Representation Learning over Dynamic Graphs
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
• Attributed Graph Clustering: A Deep Attentional Embedding Approach
• Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
• Learning physical properties of anomalous random walks using graph neural networks
• Graph Representation Learning via Graphical Mutual Information Maximization
• Data Poisoning Attack against Unsupervised Node Embedding Methods
• Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds
• AEGCN: An Autoencoder-Constrained Graph Convolutional Network
• All SMILES Variational Autoencoder
• Graph Normalizing Flows
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
• A Flexible Generative Framework for Graph-based Semi-supervised Learning
• Spectral-based Graph Convolutional Network for Directed Graphs
• Graph Representation Learning for Road Type Classification
• Graph neural network-based fault diagnosis: a review
• Learning Graph Neural Networks with Positive and Unlabeled Nodes
• Graphite: Iterative Generative Modeling of Graphs
• Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
• Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks
• Joint embedding of structure and features via graph convolutional networks
• Inductive Representation Learning on Temporal Graphs
• A Tutorial on Deep Latent Variable Models of Natural Language
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Edge-based sequential graph generation with recurrent neural networks
• Graph Neural Networks: Methods, Applications, and Opportunities
• Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders
• Adversarial Autoencoders with Constant-Curvature Latent Manifolds
• Overlapping Community Detection with Graph Neural Networks
• Large-Scale Representation Learning on Graphs via Bootstrapping
• Meta-Graph: Few Shot Link Prediction via Meta Learning
• A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks
• Semantic and Relational Spaces in Science of Science: Deep Learning Models for Article Vectorisation
• Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning
• Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
• Implementing graph neural networks with TensorFlow-Keras
• RWR-GAE: Random Walk Regularization for Graph Auto Encoders
• Convolutional Set Matching for Graph Similarity
• GraphCL: Contrastive Self-Supervised Learning of Graph Representations
• Bayesian graph convolutional neural networks via tempered MCMC
• Attributed Graph Clustering via Adaptive Graph Convolution
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
• CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning
• A Survey of Knowledge Enhanced Pre-trained Models
• Revisiting Bayesian Autoencoders with MCMC
• Link Prediction Adversarial Attack
• ROD: Reception-aware Online Distillation for Sparse Graphs
• Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels
• Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• Automated Self-Supervised Learning for Graphs
• Line Hypergraph Convolution Network: Applying Graph Convolution for Hypergraphs
• Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset for Intelligent Vehicles
• Multi-Task Graph Autoencoders
• Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
• GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
• Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
• Local Augmentation for Graph Neural Networks
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder
• Graph Generation with Variational Recurrent Neural Network
• Extraction of Airways using Graph Neural Networks
• Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
• Set2Graph: Learning Graphs From Sets
• SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
• Hyperbolic Node Embedding for Signed Networks
• Learning to Drop: Robust Graph Neural Network via Topological Denoising
• SWAG: Item Recommendations using Convolutions on Weighted Graphs
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder
• Relating Graph Neural Networks to Structural Causal Models
• Bayesian Spatio-Temporal Graph Convolutional Network for Traffic Forecasting
• Intent Disentanglement and Feature Self-supervision for Novel Recommendation
• GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction
• Meta-Learning with Graph Neural Networks: Methods and Applications
• Towards Probabilistic Generative Models Harnessing Graph Neural Networks for Disease-Gene Prediction
• Node Similarity Preserving Graph Convolutional Networks
• Deep Representation Learning for Social Network Analysis
• Variational Autoencoder for Anti-Cancer Drug Response Prediction
• Stability and Generalization of Graph Convolutional Neural Networks
• Generative Adversarial Zero-shot Learning via Knowledge Graphs
• SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation
• Neural Link Prediction with Walk Pooling
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• Tri-graph Information Propagation for Polypharmacy Side Effect Prediction
• Deep Hyperedges: a Framework for Transductive and Inductive Learning on Hypergraphs
• Adversarial Classifier for Imbalanced Problems
• FedGL: Federated Graph Learning Framework with Global Self-Supervision
• Generative Graph Convolutional Network for Growing Graphs
• Predicting potential drug targets and repurposable drugs for COVID-19 via a deep generative model for graphs
• Benchmarks for Graph Embedding Evaluation
• Dirichlet Graph Variational Autoencoder
• Graph Meta Learning via Local Subgraphs
• Graph Convolutional Networks for traffic anomaly
• Latent Variable Modelling with Hyperbolic Normalizing Flows
• A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction
• Self-supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection
• RepGN:Object Detection with Relational Proposal Graph Network
• DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
• On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
• Context-Aware Visual Compatibility Prediction
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
• Network Representation Learning: Consolidation and Renewed Bearing
• SCE: Scalable Network Embedding from Sparsest Cut
• From Local Structures to Size Generalization in Graph Neural Networks
• Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
• Size-Invariant Graph Representations for Graph Classification Extrapolations
• VersaGNN: a Versatile accelerator for Graph neural networks
• GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
• Deep Generative Graph Distribution Learning for Synthetic Power Grids
• Graph Generators: State of the Art and Open Challenges
• Mixed Pooling Multi-View Attention Autoencoder for Representation Learning in Healthcare
• Secure Deep Graph Generation with Link Differential Privacy
• Cascade-BGNN: Toward Efficient Self-supervised Representation Learning on Large-scale Bipartite Graphs
• SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations
• Learning Large-scale Location Embedding From Human Mobility Trajectories with Graphs
• Deconvolutional Networks on Graph Data
• Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation
• ResGCN: Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks
• Tiered Latent Representations and Latent Spaces for Molecular Graphs
• Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
• Cross-GCN: Enhancing Graph Convolutional Network with $k$-Order Feature Interactions
• Unsupervised Cyberbullying Detection via Time-Informed Gaussian Mixture Model
• Hebbian Graph Embeddings
• Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
• ANAE: Learning Node Context Representation for Attributed Network Embedding
• Modeling Graphs with Vertex Replacement Grammars
• Graph-Aware Transformer: Is Attention All Graphs Need?
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
• Exploring the Representational Power of Graph Autoencoder
• Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
• Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference
• Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction
• CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering
• GraphAttacker: A General Multi-Task GraphAttack Framework
• SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks
• Self-supervised Document Clustering Based on BERT with Data Augment
• Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
• Node2Seq: Towards Trainable Convolutions in Graph Neural Networks
• Graph Autoencoders with Deconvolutional Networks
• Edge Proposal Sets for Link Prediction
• Semi-Supervised Learning on Graphs Based on Local Label Distributions
• Representation Learning on Graphs: A Reinforcement Learning Application
• Graph Convolutional Network-based Suspicious Communication Pair Estimation for Industrial Control Systems
• Pre-training Graph Transformer with Multimodal Side Information for Recommendation
• Deep Attention-guided Graph Clustering with Dual Self-supervision
• Unsupervised Deep Manifold Attributed Graph Embedding
• Adaptive Graph Auto-Encoder for General Data Clustering
• Semi-supervised Anomaly Detection on Attributed Graphs
• Which way? Direction-Aware Attributed Graph Embedding
• SMASH: Sparse Matrix Atomic Scratchpad Hashing
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• Adversarial Graph Disentanglement
• Tiered Graph Autoencoders with PyTorch Geometric for Molecular Graphs
• A framework for constructing a huge name disambiguation dataset: algorithms, visualization and human collaboration
• R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning
• Towards Interpretable Graph Modeling with Vertex Replacement Grammars
• dynnode2vec: Scalable Dynamic Network Embedding
• GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations
• Deep Contrastive Graph Representation via Adaptive Homotopy Learning
• Graph Embeddings at Scale
• Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
• Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders
• Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference
• Adversarial Privacy Preserving Graph Embedding against Inference Attack
• Integrating Network Embedding and Community Outlier Detection via Multiclass Graph Description
• Modularity Optimization as a Training Criterion for Graph Neural Networks
• Accelerating science with human versus alien artificial intelligences
• Graph Cross Networks with Vertex Infomax Pooling
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank
• Node Copying: A Random Graph Model for Effective Graph Sampling
• Self-Constructing Graph Convolutional Networks for Semantic Labeling
• Multi-Label Graph Convolutional Network Representation Learning
• The general theory of permutation equivarant neural networks and higher order graph variational encoders
• Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
• Graph-based State Representation for Deep Reinforcement Learning
• A Robust and Generalized Framework for Adversarial Graph Embedding
• Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation
• Evaluating Modules in Graph Contrastive Learning
• GraphMI: Extracting Private Graph Data from Graph Neural Networks
• Continuous Graph Flow
• What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning
• Graph Representation Learning on Tissue-Specific Multi-Omics
• PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
• The Atlas for the Aspiring Network Scientist
• Two-pronged Strategy: Lightweight Augmented Graph Network Hashing for Scalable Image Retrieval
• Attention-driven Graph Clustering Network
• Structure-Aware Generation Network for Recipe Generation from Images
• BayReL: Bayesian Relational Learning for Multi-omics Data Integration
• Unsupervised Joint $k$-node Graph Representations with Compositional Energy-Based Models
• The Infinity Mirror Test for Graph Models
• Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder
• DeepNC: Deep Generative Network Completion
• FedGraph: Federated Graph Learning with Intelligent Sampling
• GRADE: Graph Dynamic Embedding
• Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations
• Auto-decoding Graphs
• REMAX: Relational Representation for Multi-Agent Exploration
• On Learning Combinatorial Patterns to Assist Large-Scale Airline Crew Pairing Optimization
• Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)
• Deep Generative Modeling in Network Science with Applications to Public Policy Research
• ConTIG: Continuous Representation Learning on Temporal Interaction Graphs
• Explainable Recommender Systems via Resolving Learning Representations
• Deep Dual Support Vector Data Description for Anomaly Detection on Attributed Networks
• DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding
• A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
• Local2Global: Scaling global representation learning on graphs via local training
• On the combination of graph data for assessing thin-file borrowers' creditworthiness
• Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning
• SHADOWCAST: Controllable Graph Generation
• Multi-Zone Unit for Recurrent Neural Networks
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
• Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
• Generating a Doppelganger Graph: Resembling but Distinct
• Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach
• Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders
• Multi-view Contrastive Graph Clustering
• Edge: Enriching Knowledge Graph Embeddings with External Text
• Signed Graph Attention Networks
• GraphCode2Vec: Generic Code Embedding via Lexical and Program Dependence Analyses
• Neural Variational Inference For Estimating Uncertainty in Knowledge Graph Embeddings
• Instance-Dependent Partial Label Learning
• Inductive Subgraph Embedding for Link Prediction
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
• Towards Automated Evaluation of Explanations in Graph Neural Networks
• MOOCRep: A Unified Pre-trained Embedding of MOOC Entities
• Inductive Matrix Completion Using Graph Autoencoder
• Latent Network Embedding via Adversarial Auto-encoders
• On the Power of Edge Independent Graph Models
• Wasserstein Adversarially Regularized Graph Autoencoder
• Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings
• Metapaths guided Neighbors aggregated Network for?Heterogeneous Graph Reasoning
• Temporal Network Representation Learning via Historical Neighborhoods Aggregation
• Micro-supervised Disturbance Learning: A Perspective of Representation Probability Distribution
• Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning
• Stable and Discriminative Topological Graph Analysis
• Equipping SBMs with RBMs: An Explainable Approach for Analysis of Networks with Covariates
• SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
• Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization
• Graph Neural Networks for Node-Level Predictions
• Mutual Information Maximization in Graph Neural Networks
• About Graph Degeneracy, Representation Learning and Scalability
• Graph Embedding VAE: A Permutation Invariant Model of Graph Structure
• Dynamic Graph Embedding via LSTM History Tracking
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification
• GraSSNet: Graph Soft Sensing Neural Networks
• CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations
• Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs
• DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks
• Link Analysis meets Ontologies: Are Embeddings the Answer?
• SCG: Spotting Coordinated Groups in Social Media
• Partitioned Graph Convolution Using Adversarial and Regression Networks for Road Travel Speed Prediction
• Graph Minors Meet Machine Learning: the Power of Obstructions
• Knowledge Generation -- Variational Bayes on Knowledge Graphs
• Investigating Estimated Kolmogorov Complexity as a Means of Regularization for Link Prediction
• Action Recognition with Kernel-based Graph Convolutional Networks
• Simplex Initialization: A Survey of Techniques and Trends
• Network representation learning: A macro and micro view
• Grounded Graph Decoding Improves Compositional Generalization in Question Answering
• Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains
• Node Attribute Generation on Graphs
• VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
• MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
• Node Copying for Protection Against Graph Neural Network Topology Attacks
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels?
• Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations
• Deep Human-guided Conditional Variational Generative Modeling for Automated Urban Planning
• Attributed Graph Modeling with Vertex Replacement Grammars
• Co-embedding of Nodes and Edges with Graph Neural Networks
• Automated Feature-Topic Pairing: Aligning Semantic and Embedding Spaces in Spatial Representation Learning
• Grouping Search Results with Product Graphs in E-commerce Platforms
• Decoupled Variational Embedding for Signed Directed Networks
• Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
• Learning to Sample Hard Instances for Graph Algorithms
• Training Graph Neural Networks by Graphon Estimation
• Beyond Observed Connections : Link Injection
• Analysis of 5G academic Network based on graph representation learning method
• Anomaly Detection for Aggregated Data Using Multi-Graph Autoencoder
• On Generalization of Graph Autoencoders with Adversarial Training
• FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding
• The Impact of Negative Sampling on Contrastive Structured World Models
• Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning
• Dynamic Joint Variational Graph Autoencoders
• Barlow Graph Auto-Encoder for Unsupervised Network Embedding
• X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering
• Decoupling feature propagation from the design of graph auto-encoders
• Scalable Deep Generative Relational Models with High-Order Node Dependence
• Graph Diffusion-Embedding Networks
• Leveraging Hidden Structure in Self-Supervised Learning
• Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering
• Generating the Graph Gestalt: Kernel-Regularized Graph Representation Learning
• Graph2Graph Learning with Conditional Autoregressive Models
• Dynamic Embedding on Textual Networks via a Gaussian Process
• Variational Composite Autoencoders
• A Block-based Generative Model for Attributed Networks Embedding
• DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction
• Network-principled deep generative models for designing drug combinations as graph sets
• DSSLP: A Distributed Framework for Semi-supervised Link Prediction
• Bipartite Link Prediction based on Topological Features via 2-hop Path
• Complex network prediction using deep learning
• Bidirectional group random walk based network embedding for asymmetric proximity
• Speaker diarization with session-level speaker embedding refinement using graph neural networks
• Learning Graphon Autoencoders for Generative Graph Modeling
• Generative Temporal Link Prediction via Self-tokenized Sequence Modeling
• A Novel Column Generation Heuristic for Airline Crew Pairing Optimization with Large-scale Complex Flight Networks
• OPAL-Net: A Generative Model for Part-based Object Layout Generation
• Modeling Heterogeneous Edges to Represent Networks with Graph Auto-Encoder