graph neural networks
PulseAugur coverage of graph neural networks — every cluster mentioning graph neural networks across labs, papers, and developer communities, ranked by signal.
- instance of GNNs and Graph Generative models for biomedical applications 90%
- used by GNNs and Graph Generative models for biomedical applications 70%
- developed Graph Neural Networks (GNNs) 70%
- developed by Graph Neural Networks (GNNs) 70%
- uses finite element method 60%
- affiliated with finite element method 50%
- 2026-05-25 research_milestone Researchers proposed new polynomial-time algorithms for explaining Graph Neural Networks. source
- 2026-05-13 research_milestone A new graph neural network architecture was introduced for the multicut problem. source
- 2026-05-11 research_milestone A new method for pre-training GNNs using ECFPs shows improved performance in QSAR tasks. source
22 day(s) with sentiment data
-
New benchmark evaluates GNN graph coarsening for chip design
Researchers have introduced CTS-Bench, a new benchmark suite designed to evaluate the trade-offs between graph coarsening techniques and the accuracy of Graph Neural Networks (GNNs) for Clock Tree Synthesis (CTS) in ele…
-
New GNN attack and defense methods proposed
Researchers have developed new methods for attacking and defending graph neural networks (GNNs) against information leakage. The study characterizes how graph properties like homophily and heterophily influence the reco…
-
Pharmacogenomic data boosts drug-drug interaction prediction with GNNs
Researchers have developed a method to enhance drug-drug interaction (DDI) prediction using Graph Neural Networks (GNNs) by incorporating pharmacogenomic data. This approach augments molecular structure information with…
-
New topological framework characterizes GNNs for transfer learning
Researchers have developed a novel topological framework to analyze and compare trained Graph Neural Networks (GNNs). This method maps the induced Stochastic Block Models onto the unit n-sphere, creating a low-dimension…
-
New defense system ADAGE prevents Graph Neural Network theft
Researchers have introduced ADAGE, a novel active defense system designed to prevent the theft of Graph Neural Networks (GNNs). Unlike previous defenses that focused on identifying stolen models, ADAGE proactively monit…
-
GNNs can now execute graph algorithms exactly, researchers find
Researchers have developed a method to enable Graph Neural Networks (GNNs) to precisely execute graph algorithms. Their approach involves training Multi-Layer Perceptrons (MLPs) to handle local node instructions, which …
-
New research details optimal graph structures for relational deep learning
Researchers have identified key characteristics that make graphs suitable for relational deep learning. They found that directly converting database schemas into graphs often leads to information overload and semantic f…
-
New framework tests GNNs against calibration attacks
Researchers have developed a new framework called the Unified Graph Calibration Attack (UGCA) to test the robustness of Graph Neural Networks (GNNs) against adversarial perturbations. This framework addresses challenges…
-
GeoGNN uses graph neural networks for time series geolocalization
Researchers have developed GeoGNN, a novel two-tower graph neural network architecture for time series geolocalization. This method infers the geographic origin of time series data by learning embeddings from both geogr…
-
New LCC classifier boosts GNN performance on heterophilous graphs
Researchers have developed a new classifier called Label Context Classifier (LCC) to improve node classification in heterophilous graphs. Current Graph Neural Networks (GNNs) struggle with these graphs where nodes with …
-
HOPSE framework boosts scalability for higher-order AI representations
Researchers have developed HOPSE, a new framework designed to enhance the scalability of Topological Deep Learning. This approach moves away from traditional message-passing layers, instead utilizing Hasse graph decompo…
-
New HPME framework enhances GNN explainability with hard perturbations
Researchers have developed a new framework called HPME to improve the explainability of Graph Neural Networks (GNNs). Existing methods often struggle with 'soft masks' that allow irrelevant information to persist, hinde…
-
New PAC-Bayesian framework enhances adversarial robustness analysis for GNNs
Researchers have developed a new PAC-Bayesian framework to analyze the adversarial robustness of message passing graph neural networks (MPGNNs). This framework offers tighter generalization bounds by quantifying paramet…
-
New method rivals graph neural networks using tabular techniques
Researchers have introduced Fixed Aggregation Features (FAFs), a novel training-free method that reframes graph learning tasks as tabular problems. This approach allows for the use of standard tabular machine learning t…
-
New method tackles noisy labels in Graph Neural Networks
Researchers have developed a new method called ICGNN to improve the robustness of Graph Neural Networks (GNNs) when dealing with noisy labels. The approach uses a novel noise indicator, the influence contradiction score…
-
New Bayesian Privacy Framework for Graph Neural Networks
Researchers have introduced Bayesian Membership Privacy (BMP), a new framework for assessing privacy in Graph Neural Networks (GNNs). BMP accounts for structural correlations and stochastic training-graph sampling, whic…
-
Graph neural network predicts PROTAC protein degradability
Researchers have developed DegradoMap, a new graph neural network designed to predict the degradability of proteins targeted by PROTACs. Unlike previous methods requiring complete PROTAC structures, DegradoMap uses only…
-
New RIDE dataset standardizes train delay prediction benchmark
Researchers have introduced RIDE, a new open dataset and benchmark designed to standardize train delay prediction. This nationwide dataset, covering the Belgian railway network from 2023 to 2025, includes 94.5 million t…
-
New framework ADPrompt enhances fairness in graph neural networks
Researchers have introduced Adaptive Dual Prompting (ADPrompt), a new framework designed to make Graph Neural Networks (GNNs) fairer. Existing methods often overlook biases present in graph data, leading to unfair outco…
-
New GNN model improves Alzheimer's classification using brain network analysis
Researchers have developed a new multi-modal graph neural network designed to improve the classification of preclinical Alzheimer's disease. The model integrates a transformer with a diffusion process to better capture …