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 Graph Neural Networks (GNNs) 95%
- instance of GNNs and Graph Generative models for biomedical applications 90%
- instance of graph attention network 90%
- instance of graph convolutional network 90%
- instance of Graphsage 90%
- instance of Graph Convolutional Networks 90%
- used by Link prediction 90%
- used by Gotit.pub 70%
- used by ScienceCast 70%
- used by alphaXiv 70%
- used by CatalyzeX 70%
- instance of Gotit.pub 70%
- 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
20 day(s) with sentiment data
-
New framework enables exact Aumann-Shapley attribution for GNNs
Researchers have developed APEX, a novel framework designed to provide exact Aumann-Shapley attributions for graph neural networks (GNNs). This framework utilizes a specialized GNN architecture called PolyGIN, which mai…
-
AI-powered GNNs optimize urban V2X relay selection
Researchers have developed a new framework using Graph Neural Networks (GNNs) to improve real-time relay selection for NR-V2X communications in urban environments. This approach models vehicular communication states as …
-
SeeExplainer method enhances GNN interpretability by capturing synergistic edge effects
Researchers have developed SeeExplainer, a new method for interpreting graph neural networks (GNNs) by focusing on the synergistic effects of edges. Unlike previous approaches that assess edge importance individually, S…
-
New framework LC-SLab enhances land cover mapping with object-based deep learning
Researchers have developed LC-SLab, a novel deep learning framework designed for large-scale land cover classification using satellite imagery and sparse in-situ labels. This object-based approach assigns labels to cohe…
-
Graph Neural Networks Improve Groundwater Arsenic Prediction
Researchers have developed graph neural networks (GNNs) to predict groundwater arsenic concentrations, addressing a significant public health issue in the United States. By integrating data from over 74,000 arsenic samp…
-
New loss function improves graph neural networks for recommendations
Researchers have developed a new method called Cardinality-Decomposed Loss (CDL) to improve the performance of graph neural networks in recommendation systems. Traditional methods often use a single loss function like B…
-
New adversarial attack targets GNN-based anomaly detection in sensor networks
Researchers have developed BETA, a novel indirect adversarial attack designed to compromise graph neural network (GNN) based anomaly detection systems in sensor networks. This attack method allows an adversary to pertur…
-
Graph Neural Networks accelerate catalyst design for graphene quantum dots
Researchers have developed a novel framework utilizing graph neural networks (GNNs) to significantly accelerate the exploration of transition metal adsorption on graphene quantum dots (GQDs). This GNN-based model, named…
-
New GNODE method improves unsteady airfoil aerodynamics prediction
Researchers have developed a new method called GNODE, which combines Graph Neural Ordinary Differential Equations (GNODEs) with augmented Neural Ordinary Differential Equations to predict unsteady airfoil aerodynamics. …
-
New algorithm boosts Neural Markov Logic Networks for relational structure generation
Researchers have introduced Parallel Noising, a novel training and inference algorithm designed to enhance Neural Markov Logic Networks (NMLNs). This new method, inspired by parallel-tempering Markov chain Monte Carlo t…
-
New GUIDED layer enhances GNNs for traffic assignment, cuts training time
Researchers have developed a novel network-agnostic initialization layer called Geometrically Unconstrained Inductive Demand EmbeDding (GUIDED) to address the spatial generalization gap in Graph Neural Networks (GNNs) u…
-
New MR-ConceptGCN model enhances sequential learner modeling
Researchers have developed MR-ConceptGCN, a novel unsupervised approach for sequential learner modeling that utilizes multi-relational graph convolutional networks. This method enhances user modeling by effectively comb…
-
New research tackles text-attributed graph learning challenges
Two new research papers introduce methods and benchmarks for improving the learning capabilities of text-attributed graphs (TAGs), which combine relational structures with textual data. The first paper, "Semi-Supervised…
-
Graph Transformers for MILPs Limited by 1-WL Test, Study Finds
A new paper characterizes the expressive power of global-attention graph transformers used for mixed-integer linear programs (MILPs). The research proves that these models, including architectures like Graphormer and Se…
-
Graph Neural Networks explored as metamodels for supply chain optimization
A new paper introduces the potential of Graph Neural Networks (GNNs) as metamodels for supply chain optimization, a largely unexplored area. The research outlines key directions, presents a foundational public dataset o…
-
New GNN architecture mHC-GNN tackles over-smoothing and expressiveness limits
Researchers have developed a new Graph Neural Network (GNN) architecture called mHC-GNN, which addresses the common issues of over-smoothing and limited expressiveness in deep GNNs. By adapting manifold-constrained hype…
-
Graph Neural Networks Learn Structural Manipulability in Hardware Designs
Researchers have developed a method to quantify the structural manipulability of gate-level netlists, which are foundational to hardware design. This score characterizes node-level flexibility by analyzing path particip…
-
Survey details GNN-based link prediction techniques and applications
This paper offers a comprehensive survey of Graph Neural Network (GNN)-based link prediction techniques. It introduces a new taxonomy to categorize advancements by GNN encoder architectures, such as GCN-based, GAE-based…
-
Graph Neural Networks struggle to predict stability in complex oscillator networks
A new research paper explores the limitations of network measures and machine learning, including Graph Neural Networks (GNNs), in predicting the stability of complex oscillator networks. The study found that while GNNs…
-
Study questions effectiveness of heterogeneous graph neural networks for node classification
A new study published on arXiv investigates the effectiveness of heterogeneous graph neural networks (HGNNs) for node classification. Researchers conducted extensive reproductions across 21 datasets and 20 baseline mode…