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
21 day(s) with sentiment data
-
New papers explore GNNs for general use and reliable decision-making
Two new research papers explore advancements in Graph Neural Networks (GNNs). The first paper provides an introductory overview of GNNs for machine learning engineers, detailing their framework, applications, and challe…
-
Explainable GNNs pose security risk, enabling model theft
Researchers have identified a significant security vulnerability in explainable Graph Neural Networks (GNNs). These explainability features, designed to increase transparency, can inadvertently leak critical decision lo…
-
Plain Transformer model PENCIL outperforms GNNs in graph link prediction
Researchers have developed PENCIL, a plain Transformer model that can predict links in large graphs more efficiently than traditional Graph Neural Networks (GNNs). Unlike existing Graph Transformers that require complex…
-
New GJDNet framework boosts GNN robustness against adversarial attacks
Researchers have developed GJDNet, a novel framework designed to enhance the robustness of Graph Neural Networks (GNNs) against adversarial attacks. These attacks exploit structural inversions in graph connectivity, lea…
-
New framework scales higher-order graph learning with clique complexes
Researchers have developed a new framework for higher-order graph learning that addresses the scalability limitations of existing methods. The approach introduces simplified and factored cellular Weisfeiler Leman tests …
-
Graph neural networks lack continuity across resolutions, study finds
Researchers have demonstrated that graph neural networks (GNNs) are not consistently continuous across different graph resolutions. This lack of continuity can lead to significantly different latent representations for …
-
AI Fusion Stack Enhances Military Intelligence with LLMs and Knowledge Graphs
Modern military intelligence is leveraging a fusion stack of Graph Neural Networks (GNNs), Large Language Models (LLMs), and knowledge graphs to overcome the limitations of traditional AI in dynamic, adversarial environ…
-
SemStruct framework improves schema matching using PLMs and GNNs
Researchers have developed SemStruct, a new framework for schema matching that combines the semantic understanding of pre-trained language models (PLMs) with the structural analysis capabilities of Graph Neural Networks…
-
Survey paper on GNN graph rewiring accepted at IJCAI 2026
A survey paper on graph rewiring techniques for Graph Neural Networks (GNNs) has been accepted at IJCAI 2026. The paper addresses the challenges of over-squashing and over-smoothing in GNNs, which hinder information flo…
-
Graph Navier Stokes Networks combat oversmoothing with convection
Researchers have introduced Graph Navier Stokes Networks (GNSN), a novel architecture for Graph Neural Networks designed to overcome the oversmoothing problem. Unlike traditional diffusion-based methods, GNSN incorporat…
-
New ORACAL framework boosts smart contract vulnerability detection
Researchers have developed ORACAL, a new multimodal framework designed to enhance the detection of smart contract vulnerabilities. This framework integrates various graph representations like Control Flow Graph, Data Fl…
-
New GRaNDe method boosts GNN accuracy in image classification
Researchers have developed a new method called GRaNDe (Gaussian Rank-based Neighborhood Degree) to improve Graph Neural Networks (GNNs) for image classification. This technique addresses the limitation of traditional GN…
-
Researchers propose explainable GNN ensemble for malware detection
Researchers have developed a novel ensemble framework using stacked graph neural networks (GNNs) for improved malware detection. This method dynamically extracts control flow graphs from executable files and uses multip…
-
GNNs struggle to approximate sparse matrix factorizations
A new research paper demonstrates that standard message-passing Graph Neural Networks (GNNs) are fundamentally unable to approximate sparse triangular factorizations. The study shows that even advanced architectures lik…
-
New ASTRO framework uses RL and GNNs for cyber-physical anomaly detection
Researchers have developed ASTRO, a new anomaly detection framework for cyber-physical systems that utilizes reinforcement learning and Graph Neural Networks. ASTRO dynamically optimizes decision boundaries by integrati…
-
New methods optimize LLM multi-agent system prompts
Researchers have developed novel methods for optimizing prompts in multi-agent systems (MAS) powered by large language models (LLMs). One approach, MASPOB, uses bandit algorithms and graph neural networks to efficiently…
-
New framework enhances privacy and efficiency for federated graph neural networks
Researchers have developed a new framework called CE-FedGNN for training graph neural networks (GNNs) on distributed datasets. This method addresses the challenges of privacy and communication costs associated with fede…
-
GP2F method enhances cross-domain graph neural network adaptation
Researchers have introduced GP2F, a novel method for cross-domain graph prompting that aims to improve the adaptation of pre-trained graph neural networks to new tasks. The method is based on theoretical analysis showin…
-
New logic-based graph learning method rivals GNNs in speed and performance
Researchers have developed new variants of the Weisfeiler-Leman algorithm for graph classification, which involve modifying the underlying logical framework. These variants allow graph data to be tabularized, enabling t…
-
New GNN defense uses self-supervised purifier against adversarial attacks
Researchers have developed a novel self-supervised adversarial purification framework for Graph Neural Networks (GNNs). This new method separates the task of robustness from classification by using a dedicated purifier,…