A new model for multiview data analysis using graph autoencoders.
problem Nonlinear multiview canonical correlation analysis for large datasets.
method Variational approach with graph convolutional neural networks.
result Competitive performance on classification, clustering, and recommendation tasks.
Adversarial training improves graph autoencoder generalization.
problem Improving graph autoencoder generalization.
method Formulated L2 and L1 adversarial training for graph autoencoders and variational graph autoencoders.
result Adversarial training boosts graph autoencoder and variational graph autoencoder generalization.
Automates molecule design with a novel variational autoencoder.
problem Designing molecules based on specific chemical properties.
method Junction tree variational autoencoder generating tree-structured scaffolds and combining them into molecules.
result Significantly outperforms previous models on molecular generation and optimization tasks.
RL-VAE uses RL to decode molecular graphs from latent embeddings.
problem Efficiently decoding molecular graphs from latent embeddings.
method Repurposed simple graph generator for efficient decoding.
result Decoding molecular graphs from latent embeddings is possible with a simple graph generator.
A new model learns latent spaces for graph data.
problem Scalability and expressivity limitations in graph generative models.
method Sequential Graph Variational Autoencoder (SGVAE) that learns latent spaces directly from graph data.
result Promising results on a cycle dataset, but need for permutation relaxation.
New framework scales graph AE and VAE by training on a subset of nodes.
problem Training scalability and speed issues in graph AE and VAE models.
method Utilizes graph degeneracy to train on a dense subset of nodes, with a propagation mechanism.
result Empirically competitive results on large graphs (millions of nodes and edges).
EVGAE improves VGAE's latent representation learning by mitigating over-pruning.
problem Over-pruning in VGAE limits latent variable capacity and diversity.
method EVGAE uses epitomic approach with multiple sparse VGAE models (epitomes) to increase active latent units and improve generative ability.
result EVGAE outperforms VGAE in generative ability and link prediction on citation networks.
Graph autoencoder learns molecule designs matching training data.
problem Learning to generate molecules that match training data statistics.
method Graph-structured variational autoencoder with sequential graph extension.
result Our model designs molecules that are locally optimal in desired properties.
Paper proposes a novel adversarial framework for graph embedding.
problem Graph embedding often fails to represent latent codes effectively.
method Adversarial training to enforce latent codes to match a prior distribution.
result ARGA and ARVGA models improve graph embedding for link prediction and clustering.
New graph AE and VAE model predicts directed links better than existing methods.
problem Link prediction in directed graphs, especially for unobserved edges.
method Gravity-inspired decoder scheme for directed graphs.
result Outperforms standard graph AE and VAE on three real-world directed link prediction tasks.
DefenseVGAE defends graph neural networks against adversarial attacks.
problem Vulnerability of GNNs to adversarial structural perturbations.
method Variational Graph Autoencoder (VGAE) to reconstruct graph structure.
result DefenseVGAE reduces adversarial perturbations and boosts GCN performance.
This work tackles semantic validity in graph generation, proposing a regularization framework for variational autoencoders.
problem Ensuring semantic validity in graph generation, especially for combinatorial structures like molecular graphs and protein interaction networks.
method Proposes a regularization framework for variational autoencoders to enforce semantic constraints in graph generation.
result Significantly higher likelihood of sampling valid graphs compared to existing methods.
Dyn-VGAE learns evolving network structures.
problem Learning dynamic network representations.
method Dynamic joint Variational Graph Autoencoders (Dyn-VGAE).
result Dyn-VGAE captures temporal evolution in dynamic networks.
A deep learning model organizes RNA graphs to reveal folding patterns and properties.
problem Organizing and understanding the complex folding patterns of RNA secondary structures.
method Geometric scattering autoencoder (GSAE) network for learning graph embeddings.
result GSAE accurately reflects bistable RNA structures and can sample new folding trajectories.
FastGAE scales graph AE and VAE to large graphs with millions of nodes.
problem Scalability issues in graph AE and VAE.
method Stochastic subgraph decoding scheme to speed up training.
result Outperforms existing approaches on various real-world graphs.
D-VAE generates valid DAGs for neural architecture search and Bayesian network learning.
problem Generating valid DAGs for machine learning models.
method Proposes a novel DAG variational autoencoder (D-VAE) using graph neural networks and asynchronous message passing.
result Demonstrates the effectiveness of D-VAE through neural architecture search and Bayesian network structure learning.
Tiered graph autoencoders improve molecular graph representation.
problem Representing and utilizing groups in molecular graphs.
method Adapting tiered graph autoencoders for PyTorch Geometric.
result Molecular graphs have tiered latent representations.
VACA models graph data for causal inference without hidden confounders.
problem Causal inference in observational data with hidden confounders.
method Variational graph autoencoders for structural causal models.
result Accurately approximates interventional and counterfactual distributions.
Develops scalable autoencoder for document networks.
problem Sparse and skewed latent node representations in document relational networks.
method Combines graph Poisson factor analysis with Weibull-based graph inference networks.
result Extracts high-quality hierarchical latent document representations.
Improved community detection and link prediction with GAE and VGAE.
problem Jointly improving community detection and link prediction with graph autoencoders.
method Introducing a community-preserving message passing scheme and doping encoders with Louvain-based prior communities.
result Empirical effectiveness of Modularity-Aware GAE and VGAE on various real-world graphs.
This work creates a deep autoencoding model to interpret graph parameters.
problem Matching observed graph topologies with generative procedures and parameters is challenging.
method Developed a disentanglement-focused Beta-Variational Autoencoder (Beta-VAE) model.
result The model learns disentangled latent variables that represent graph parameters.
Variational autoencoder models dynamic latent graphs for neural point processes.
problem Modeling event dynamics with changing trends over time.
method Sequential latent variable model with dynamic latent graphs.
result Higher accuracy in predicting inter-event times and event types.
Improved graph generation model for small organic molecules.
problem Graph generation models struggle with matching training distributions and require expensive graph matching.
method Introduced a message passing neural network into the GVAE's encoder and decoder.
result Demonstrated improved graph generation for small organic molecules.
Model infers street-level air quality using mobile station data.
problem Inferring air quality from limited mobile station data.
method Variational Graph Autoencoder for matrix completion on graph-based data.
result Model outperforms state-of-the-art approaches in air quality inference.
SAG-VAE learns data representations and feature relations end-to-end.
problem Vanilla VAEs cannot learn relations between features.
method Inspired by Graph Neural Networks, SAG-VAE jointly infers data representations and feature relations.
result SAG-VAE generates new data via graph convolution and is robust to perturbations.
Graph semi-supervised learning classifies points on manifold using variational autoencoders and GNN.
problem Classifying points on low-dimensional manifolds using limited labeled data.
method Model data as points on a manifold, approximate manifold with VAE, construct geometric graph, solve semi-supervised node classification with GNN.
result Generalization gap diminishes with graph size and training procedure, vanishing asymptotically.
The paper uses a graph autoencoder to learn unbiased plant-pollinator interaction embeddings.
problem Sampling bias in citizen science data affects ecological network analysis.
method Bipartite graph variational autoencoder with HSIC for fairness.
result The method mitigates sampling bias and provides unbiased embeddings.
Smooth embedding space improves NAS performance.
problem Efficiently predicting good neural architectures.
method Two-sided variational graph autoencoder.
result Smooth embedding space facilitates extrapolation to unseen architectures.
A new unpooling layer enhances graph generation in molecular models.
problem Efficient graph generation for complex models like molecules.
method Trainable unpooling layer that enlarges and restructures graphs.
result The unpooling layer improves graph generation in molecular models.
Paper proposes a new graph embedding framework to improve graph analytics.
problem Graph embedding often fails to capture the distribution of latent codes.
method Adversarial graph autoencoder framework that combines topological structure and node content.
result ARGA and ARVGA outperform baselines in link prediction, clustering, and visualization.
Simple linear model outperforms GCN in graph AE tasks.
problem Challenging tasks like link prediction and node clustering.
method Replaced GCN with a simple linear model on adjacency matrix.
result Simple model consistently reaches competitive performances.
Simpler linear models outperform complex GCN encoders for graph tasks.
problem Complex graph autoencoders and variational autoencoders.
method Replacing GCN encoders with one-hop linear models.
result Simpler linear models achieve competitive performance with fewer operations and parameters.
DAGSurv uses deep neural networks to analyze survival data based on causal graphs.
problem Analyzing survival data with causal relationships between variables.
method Variational inference-based conditional variational autoencoder for causal structured survival prediction.
result DAGSurv outperforms other survival analysis methods in predicting time-to-event.
Model predicts stable molecules with AI and physics constraints.
problem Designing stable molecules with limited data.
method Graph Scattering Variational Autoencoder with physical constraints.
result Model generates stable molecules with desired properties.
New method mitigates bias without sensitive data using causal graph and variational autoencoder.
problem Lack of fairness strategies when sensitive attributes are not collected.
method SRCVAE framework based on causal graph for inferring a proxy sensitive attribute.
result Significant improvements in fairness metrics over existing methods.
A new model designs molecular latent vectors for drug discovery.
problem Designing effective molecular descriptors from molecular structures.
method Proposes a denoising diffusion probabilistic model (DDPM) for variational autoencoding molecular graphs.
result Demonstrates superior prediction performance and robustness compared to existing approaches.
Proposes learning a hierarchical prior in VAEs to avoid over-regularization.
problem Over-regularization in VAEs with standard normal priors.
method Formulates as a constrained optimisation problem, introduces graph-based interpolation.
result Learned latent representation reflects data manifold topology and properties.
Graphite learns graph node representations using deep latent variable models.
problem Learning graph node representations for machine learning tasks.
method Graphite uses deep latent variable generative models with graph neural networks and iterative graph refinement.
result Graphite outperforms other methods on tasks like density estimation, link prediction, and node classification.
A novel disentangled graph autoencoder improves treatment effect estimation from networked observational data.
problem Treatment effect estimation from observational data is challenging due to unconfoundedness assumption and latent confounders.
method Proposes a disentangled variational graph autoencoder to disentangle latent factors and enforce factor independence.
result Extensive experiments show superior performance compared to state-of-the-art approaches.
Generative concept representations improve deep learning by handling uncertainty and integrating learning and reasoning.
problem Discriminative deep learning struggles with uncertainty and lacks integration of learning and reasoning.
method Probabilistic and generative deep learning, variational autoencoders, and generative adversarial networks.
result Generative concept representations enhance deep learning by addressing these limitations.
A new model learns graph structures from data.
problem Learning graph topologies from data.
method Proposes a learning to optimise (L2O) approach to learn graph structures from node data.
result The proposed model learns graph structures more efficiently than classic iterative algorithms.
Variational autoencoders learn deep latent models.
problem Learning deep latent-variable models.
method Principled framework using variational inference.
result Introduction to variational autoencoders and extensions.
We improve a graph generation model to accurately recover Barabási-Albert graph parameters.
problem Recover Barabási-Albert graph parameters from graph data.
method Use a disentanglement-focused deep autoencoding framework with a sequential LSTM decoder trained on graph data.
result Successfully recover Barabási-Albert graph parameters.
Modularity-aware GAE and VGAE improve community detection and link prediction.
problem Improving community detection with GAE and VGAE in the absence of node features.
method Introducing a modularity-aware message passing scheme and regularizer to GAE and VGAE encoders.
result Jointly addressing community detection and link prediction with high accuracy is possible.
Method generates counterfactual explanations for graph classifiers.
problem Generating high-quality explanations for graph predictions.
method Permutation equivariant graph variational autoencoder to traverse latent space.
result Empirically validated model is high-performing and robust.
NeVAE generates novel molecular structures with improved stability.
problem Generating novel molecular structures with stable configurations.
method A novel variational autoencoder for molecular graphs with optimized decoder.
result Optimized decoder generates molecules with 121% higher property values.
A graph VAE framework optimizes neural architectures in a continuous space.
problem Discovering efficient neural architectures in a discrete space.
method Graph VAE framework with VAE and GNN components, joint learning of predictors and decoders.
result The framework discovers powerful neural architectures with both excellent performance and high computational efficiency.
We find approximate geodesics in deep models using graph shortest paths.
problem Computational complexity of finding geodesics in high-dimensional latent spaces.
method Approximate geodesics via shortest paths in a finite graph of samples.
result Applicable to high-dimensional problems, e.g., visual data.