MoFlow generates chemically valid molecular graphs from latent representations.
problem Generating chemically valid molecular graphs from latent representations is challenging.
method MoFlow uses a flow-based approach with Glow for bond generation and a novel graph conditional flow for atom generation, ensuring chemical validity and efficiency.
result MoFlow achieves state-of-the-art performance in molecular graph generation and optimization.
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.
Valid prediction sets for dynamic graphs using conformal prediction.
problem Uncertainty quantification in dynamic graph neural networks.
method Dynamic graph unfolding for input to GNNs, combined with conformal prediction.
result Valid prediction sets with minimal assumptions, even in challenging scenarios.
HLTF generates chemically valid 3D molecules with improved topology control.
problem Generating chemically valid 3D molecules is challenging due to bond topology errors.
method HLTF uses a latent multi-scale plan for global context and a constraint-aware sampler to suppress topology-driven failures.
result HLTF achieves high validity and uniqueness on QM9 and GEOM-DRUGS datasets.
GENs model generates sparse graphs from text-based inputs, achieving high validity.
problem Efficiently modeling and generating sparse graphs with unique and valid structures.
method RNN-based GENs model trained with an examination mechanism to predict graph characters.
result Moderate to high validity achieved in LGI strings for sparse graph generation.
MolGAN generates valid small molecular graphs without graph matching.
problem Generating valid small molecular graphs efficiently.
method Adapts GANs to generate graph-structured data with reinforcement learning.
result MolGAN generates close to 100% valid compounds.
CALVER verifies causal reasoning traces, improving over voting methods in complex queries.
problem Voting fails in causal reasoning due to repeated confounding errors and multiple valid answers.
method CALVER scores structured traces against causal criteria and selects the highest-scoring candidate.
result CALVER selects valid answers more accurately than voting methods, especially with larger sample sizes.
GraphAF generates chemically valid molecules efficiently and accurately.
problem Generating chemically valid molecular structures while optimizing chemical properties.
method Flow-based autoregressive model combining autoregressive and flow-based approaches.
result GraphAF generates 68% chemically valid molecules without chemical knowledge rules and 100% with rules, achieving state-of-the-art performance.
Improves graph recovery in Gaussian graphical modeling.
problem Calibrating regularization parameters for graph recovery.
method Thresholded adaptive validation applied to graphical lasso.
result Thresholding pipeline improves graph recovery.
System validates truthfulness of statements with evidence.
problem Unverified contents in accessible information sources.
method Inference method on a knowledge graph (KG) combined with ontologies.
result System provides valid and concise evidence for false statements.
Method learns SDEs from one trajectory using GP priors and randomized cross-validation.
problem Learning SDEs from a single trajectory.
method Combining CGC and data-adapted kernels learned via randomized cross-validation.
result Efficacy, robustness, and scope of the method demonstrated in numerical experiments.
Solves model order selection for spectral graph clustering.
problem Automated selection of the correct number of clusters in spectral graph clustering.
method AMOS, a selection criterion based on asymptotic phase transition analysis.
result Validates phase transition analysis and model selection procedure on real-world data.
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.
Graph filtering framework improves semi-supervised learning efficiency.
problem Efficiently leverage unlabeled data with limited labeled data.
method Graph filtering to inject graph similarity into data features.
result Unified insights and improved modeling capabilities of label propagation and graph convolutional networks.
ECG outperforms graph clustering algorithms using ensemble method.
problem Graph clustering challenges.
method ECG combines Louvain algorithm and consensus clustering.
result ECG outperforms leading algorithms on artificial networks.
Transformers interpreted as probabilistic Laplacian Eigenmaps steps.
problem Improving transformer performance through probabilistic interpretation.
method Probabilistic Laplacian Eigenmaps model derivation and graph diffusion step.
result Subtracting identity from attention matrix improves transformer performance.
RoCP-GNN improves GNNs' robustness in graph node classification.
problem Uncertainty in GNN predictions for graph data.
method Integrates conformal prediction into GNN training for robust prediction sets.
result GNN models with size loss improve performance in node classification.
Paper proposes a black-box adversarial attack method for graph embedding models.
problem Robustness of graph embedding models against adversarial attacks.
method GF-Attack constructs a generalized adversarial attacker by the graph filter and feature matrix, performing the attack on the graph filter in a black-box fashion.
result GF-Attack can consistently make strong attacks on different graph embedding models even with small perturbations.
Study financial market efficiency using visibility graphs and ARCH models.
problem Estimating market efficiency and predicting financial instability.
method Building visibility graphs from financial time series and validating links against ARCH models.
result Proposed market indicator highly correlated with financial instability periods.
CF-GNN provides reliable uncertainty estimates for graph data.
problem Lack of rigorous uncertainty estimates in GNNs.
method Conformal prediction extended to graph-based models (CF-GNN).
result CF-GNN produces prediction sets with provable coverage probability.
Study validates saliency maps of GNNs using selective inference.
problem Reliability of GNN saliency maps in graph-structured data.
method Statistical testing framework with selective inference to control Type I error rate.
result Valid p-values for salient subgraphs, ensuring meaningful information. TG-GAN models dynamic graph evolution for continuous-time temporal graphs.
problem Challenges in modeling dynamic temporal graphs, especially in continuous time.
method Temporal Graph Generative Adversarial Network (TG-GAN) that models truncated edge sequences, time budgets, and node attributes.
result TG-GAN significantly outperforms existing methods in efficiency and effectiveness.
Dual-Primal Graph CNN learns vertex and edge features on graphs.
problem Learning features on non-Euclidean structured data like graphs.
method Alternates graph convolutional operations on graph and its dual.
result State-of-the-art results on various graph benchmarks.
Method detects changes in graph sequences, validated on real data.
problem Identifying changes in graph sequences over time.
method Maps graphs to vectors, applies statistical tests, detects changes.
result Effectiveness validated on real data sets.
The paper uses graph learning to detect valid instruments in high-dimensional data for house pricing.
problem Endogeneity bias and invalid instrument validation in high-dimensional data.
method Merge variable selection algorithms and probabilistic graphs to estimate house prices and causal structure.
result Efficient data-driven instrument selection and invalid instrument purge in high-dimensional data.
GraphNVP generates molecular graphs efficiently and reversibly.
problem Generating valid molecular graphs with desired properties.
method Decomposes graph generation into adjacency tensor and node attributes, using reversible flows.
result Efficiently generates valid molecular graphs with minimal duplicates and latent space for property generation.
Improved graph kernel performance with structural variation noise.
problem Effect of structural variation on graph kernel predictive performance.
method Introduced a noise-robust adaptation of the GraphHopper kernel and validated it on benchmark data.
result Obtained modestly improved predictive performance on a range of datasets.
Extends graph encoder embedding to weighted graphs and matrices.
problem Classifying vertices in various graph types efficiently.
method Graph encoder embedding applied to weighted graphs, distance matrices, and kernel matrices.
result The method achieves asymptotic normality, enabling optimal classification.
Cross-GCN models cross features in GCN for better performance.
problem GCN's lack of cross feature modeling limits its effectiveness.
method Introduces Cross-feature Graph Convolution (Cross-GCN) to model cross features explicitly.
result Explicit cross feature modeling improves GCN's performance on tasks requiring cross features.
Generative model for discrete objects using Markov chains with valid transitions.
problem Generating valid discrete objects with unique construction histories.
method Markov chain with restricted local operations that preserve validity.
result Generative model produces valid discrete objects and compares favorably to alternatives.
Method learns sparse graph for multivariate data prediction efficiently.
problem Prediction of multivariate data processes using sparse graph models.
method Recursive learning of sparse partial correlation graph without cross-validation or tuning.
result Significant performance gains in prediction compared to existing graphs.
Paper describes eigenvalues of genus 3 surfaces graphs.
problem Understanding eigenvalues of genus 3 surfaces.
method Analyzes graphs derived from pair of pants decompositions.
result Complete description of eigenvalue sets for genus 3.
Estimates price elasticity from autocorrelated time series using causal graphs.
problem Inconsistent IV estimators in autocorrelated time series data.
method Model equilibrium with unobserved confounders, derive DAG, and use graphical inference for valid IV estimators.
result Valid IV estimators improve understanding of economic dynamics.
New kernel improves graph classification accuracy.
problem Improving graph classification accuracy.
method Developed an optimal assignment kernel for graphs.
result Improved graph classification accuracy on benchmark data.
We consider the problem of signal recovery on graphs as graphs model data with complex structure as signals on a graph. Graph signal recovery implies recovery of one or multiple smooth graph signals from noisy, corrupted, or incomplete measurements. We propose a graph signal model and formulate signal recovery as a cor…
New model learns from random graph samples to estimate graph parameters.
problem Scalability issues in graph learning methods for large graphs.
method Develops a graph classification model working on randomly sampled subgraphs.
result Validates mini-batch learning on graphs and provides generalization bounds.
Paper explores deeper insights into GCNs for semi-supervised learning.
problem Limited labeled data for training graph convolutional networks.
method Developed deeper insights into GCN mechanisms, proposing co-training and self-training approaches.
result Significantly improved GCNs' performance with very few labels.
Line graph transformation aids graph isomorphism tests by excluding challenging graph properties.
problem Limited theoretical understanding of line graph transformation's impact on GNN models.
method Examined CFI and strongly regular graphs, showing line graph transformation helps WL tests distinguish these graphs.
result Line graph transformation aids WL tests in distinguishing challenging graph properties.
Gaussian processes over graphs enforce specific signal profiles and outperform conventional GPs.
problem Signal processing over graphs with specific profiles.
method Graph Laplacian regularization to enforce desired signal profiles, proving predictive variance advantage.
result Gaussian processes over graphs have strictly smaller predictive variance than conventional GPs.
New framework models graph signals as distribution-valued signals in Wasserstein space.
problem Limitations of classical vector-based GSP, including synchronous observations and uncertainty.
method Introduces graph distribution-valued signals (GDSs) in the Wasserstein space.
result GDSs naturally encode uncertainty and stochasticity, generalizing traditional graph signals.
Incorrect parity-based descriptions of realizable Gauss diagrams found, but bipartite graphs provide a valid approach.
problem Incorrect descriptions of realizable Gauss diagrams using parity conditions.
method Used bipartite graphs to describe realizable Gauss diagrams.
result Realizable Gauss diagrams can be accurately described using bipartite graphs.
Paper discovers valid IVs from data without domain knowledge.
problem Inferring causal effects from observational data with latent confounders.
method Data-driven algorithm based on partial ancestral graphs (PAGs).
result Discovering valid IVs leads to accurate causal effect estimation.
LOBSTUR-GNN adapts bootstrapping for unsupervised GNNs, improving node representation learning.
problem Hyperparameter tuning and lack of established methodologies for unsupervised GNNs.
method Adapts bootstrapping techniques for local graph dependencies and uses CCA for embedding consistency.
result 65.9% improvement in classification accuracy compared to uninformed hyperparameter selection.
GNNs may be limited by graph topology, affecting their learning outcomes.
problem Understanding how graph topology influences GNN behavior and performance.
method Investigating the interaction between local topological features and GNN message-passing schemes.
result Locally similar neighborhoods can lead to consistent node representations, affecting GNN performance.
Researchers create benchmarks to compare graph inference methods.
problem Comparing graph inference methods is difficult due to varying downstream tasks.
method Developed benchmarks for various graph tasks.
result Contrasted prominent graph inference techniques.
Estimates multiple networks using graphons for non-aligned graphs.
problem Estimating topology of multiple networks from nodal observations.
method Combining maximum likelihood penalty with graphon estimation schemes.
result Validated performance against competing methods in synthetic and real-world datasets.
The paper challenges the validity of cluster validity measures in unsupervised learning.
problem The validity of cluster validity measures in selecting optimal clusterings.
method The authors investigate the use of cluster validity measures as objective functions in unsupervised learning and introduce a new variant of the Dunn index.
result Many cluster validity measures promote clusterings that do not match expert knowledge well.
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.