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 alphaXiv 90%
- developed Gotit.pub 90%
- instance of CatalyzeX 90%
- instance of IArxiv 90%
- developed CORE Recommender 90%
- instance of graph attention network 90%
- instance of Graphsage 90%
- used by Link prediction 90%
- instance of Graph Convolutional Networks 90%
- instance of MPNNs 90%
- instance of Node Classification 90%
- 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
18 day(s) with sentiment data
-
New research explores hybrid neural solvers for combinatorial optimization
Two new research papers explore advanced neural network approaches for combinatorial optimization problems. The first paper introduces HyCO, a hybrid solver that combines reinforcement learning with diffusion models to …
-
New frameworks SPEAR and SPIRE advance one-shot federated graph learning
Researchers have developed two new frameworks, SPEAR and SPIRE, to improve one-shot federated graph learning, a process where graph neural networks are trained across clients with disconnected subgraphs in a single comm…
-
New RF+ models offer interpretable network-assisted machine learning
Researchers have introduced a new family of network-assisted models called RF+, designed to improve prediction accuracy in machine learning while maintaining interpretability. These models build upon a generalization of…
-
New HOPE method tackles heterophilic graph node classification
Researchers have introduced HOPE, a novel method designed for open-set node classification in graphs that exhibit heterophily, meaning connected nodes do not necessarily share the same labels. This approach addresses li…
-
New $\alpha$-Graph method enhances graph modeling with attention-infused flows
Researchers have introduced $\alpha$-Graph, a novel Attention-based Normalizing Flow-based Approach (ANFA) designed for more effective graph modeling. This method aims to overcome limitations of traditional Graph Neural…
-
New 'Echo Chamber Effect' identified in Graph Neural Networks
Researchers have identified a new failure mode in Graph Neural Networks (GNNs) called the "Echo Chamber Effect," distinct from the known issue of oversmoothing. This effect occurs when representations within communities…
-
Machine learning methods compared for weather forecast interpolation
A new arXiv paper explores the effectiveness of various statistical and machine learning methods for interpolating weather forecast data at unobserved locations. The study, which focused on 2-m temperature and 10-m wind…
-
Robotic construction uses AI to adaptively build structures
Researchers have developed a novel reinforcement learning approach for robotic construction that bypasses the need for rigid, pre-defined plans. This method generates construction sequences adaptively by operating on gr…
-
New RGC-Net model enhances graph neural network capabilities
Researchers have introduced RGC-Net, a novel Reservoir-based Graph Convolutional Network designed to enhance information propagation and capture long-range dependencies in graph data. This new model integrates reservoir…
-
Study compares six counterfactual explanation methods for graph neural networks
A new study compares six state-of-the-art methods for generating counterfactual explanations in graph neural networks. These explanations aim to identify minimal, realistic graph modifications that change a model's pred…
-
New Physics-Aware Fingerprints Enhance Power Grid Graph Classification
Researchers have developed a new method called Multi-Channel Physics-Aware Random Walk Fingerprints (MC-PA-RWF) to improve graph classification for power grid systems. This approach incorporates physical edge states int…
-
New REMARK framework enhances GNN ownership verification
Researchers have developed REMARK, a novel framework for verifying the ownership of Graph Neural Networks (GNNs). This method addresses limitations in existing watermark and fingerprint-based techniques by generating in…
-
New GLOW framework predicts agentic workflow performance
Researchers have developed GLOW, a new framework designed to predict the performance of agentic workflows (AWs). This approach combines graph neural networks (GNNs) for structural modeling with large language models (LL…
-
Survey details Graph Foundation Models for Recommender Systems
This survey paper provides a comprehensive overview of Graph Foundation Models (GFMs) applied to recommender systems. It details how GFMs combine the strengths of graph neural networks (GNNs) for structural information …
-
GNNs vs. MLPs: Predicting Artist Success in Music Networks
A new study published on arXiv evaluates the effectiveness of Graph Neural Networks (GNNs) in predicting artist success within collaboration networks. The research introduces a dataset for the Polish music scene and com…
-
New PromptGFM model integrates LLMs and GNNs for text-attributed graphs
Researchers have introduced PromptGFM, a novel Graph Foundation Model (GFM) designed for Text-Attributed Graphs (TAGs). This model aims to improve the integration of Large Language Models (LLMs) and Graph Neural Network…
-
Graph Neural Networks Enhance Maritime Navigation Chart Safety Classification
Researchers have developed a novel approach using graph neural networks (GNNs) to classify the criticality of changes in maritime navigation charts. By representing Electronic Navigational Charts (ENCs) as graph structu…
-
New frameworks tackle cross-modal dilution and uncertainty in recommendation systems
Researchers have introduced two new frameworks for multimodal recommendation systems. LARK (Latent-Aligned Reasoning frameworK) addresses cross-modal dilution in vision-language models by using latent tokens as visual c…
-
Survey explores integrating visual graph data into AI models
A new survey paper explores the emerging field of "vision meets graphs," which integrates visual representations of graphs into machine learning models. Traditionally, graph learning has focused on symbolic structures, …
-
Graph Neural Networks Refine Bitcoin Address Clustering
Researchers have developed a new method to refine Bitcoin address clustering using graph neural networks (GNNs). This approach aims to improve the accuracy of identifying addresses belonging to the same user, addressing…