graph neural network
PulseAugur coverage of graph neural network — every cluster mentioning graph neural network across labs, papers, and developer communities, ranked by signal.
- instance of machine learning 90%
- used by knowledge graph 90%
- instance of Gotit.pub 90%
- instance of alphaXiv 90%
- instance of ScienceCast 70%
- instance of CatalyzeX 70%
- instance of DagsHub 70%
- instance of knowledge graph 70%
- uses large language model 70%
- instance of transformer 70%
- used by machine learning 70%
- instance of CNN 70%
18 day(s) with sentiment data
-
Graph Neural Networks learn algebraic properties from Cayley graphs
Researchers have developed a general framework using Graph Neural Networks (GNNs) to learn algebraic properties of finite groups directly from their Cayley graph representations. This property-independent framework was …
-
New framework aids anti-money laundering investigations with clue-guided discovery
Researchers have developed a new framework called Clue2Group to aid in anti-money laundering investigations. This framework addresses the limitations of existing methods by allowing analysts to start with a specific clu…
-
New TGHE framework enables privacy-preserving GNN inference on large graphs
Researchers have developed TGHE, a novel framework for privacy-preserving Graph Neural Network (GNN) inference in edge-cloud systems. Unlike previous graph-centric approaches that struggle with large datasets, TGHE util…
-
New method generates adversarial inputs for AC power flow GNNs
Researchers have developed a method to generate adversarial inputs for graph neural network models used in AC power flow simulations. This technique involves formulating and solving optimization problems to identify inp…
-
New study finds advanced GFMs only slightly outperform GNNs on node prediction tasks
A recent study re-evaluated nine Graph Foundation Models (GFMs) for node property prediction tasks, a common application in Graph ML used for areas like fraud detection and recommendation systems. The research found tha…
-
New AI model MORL-A2C balances health and preference in food recommendations
Researchers have developed MORL-A2C, a novel approach to enhance healthiness in personalized food recommendation systems. This method extends the existing MOPI-HFRS by employing a sequential decision-making strategy to …
-
New spectral theory for GNN propagation offers insights into signal preservation
Researchers have developed a spectral theory for normalized corrected Graph Neural Network (GNN) propagation, focusing on how this operator preserves class-discriminative signals through multiple layers. Their key findi…
-
Graph Neural Network Accelerates Superconducting Circuit Simulations
Researchers have developed SuperCond-GNN, a novel graph neural network designed to simulate superconducting circuits. This model can predict voltage distribution in high-temperature superconducting magnets, offering a s…
-
New protocol ChemGuard reveals vulnerabilities in molecular GNN backdoor attacks
Researchers have introduced ChemGuard, a new protocol to evaluate backdoor attacks on molecular graph neural networks (GNNs) by considering the chemical validity and consistency of molecular data. This approach reveals …
-
New ASR techniques tackle phonetic errors and judge reliability
Researchers are developing advanced methods to improve Automatic Speech Recognition (ASR) systems, particularly for low-resource languages and to address specific types of errors. One approach, Error-Aware TF-IDF, uses …
-
New GNN models accelerate crashworthiness simulations for vehicle components
Researchers have developed new graph neural network (GNN) architectures to improve the speed and accuracy of crashworthiness simulations for vehicle components. The first approach, Mask-Morph Graph U-Net (MMGUNet), addr…
-
New benchmark MolGraphBench evaluates GNNs for molecular regression tasks
A new benchmark called MolGraphBench has been introduced to evaluate Graph Neural Network (GNN) architectures for molecular regression tasks. The benchmark, proposed by Ishaan Gupta, analyzes four common GNN models, fin…
-
Graph neural network captures intransitive dominance for tennis forecasting
Researchers have developed a novel graph neural network (GNN) approach to forecast tennis matches by explicitly modeling intransitive player dominance. This method represents players as nodes and match outcomes as direc…
-
Graph Neural Networks accelerate physics simulations for magnets and fracture mechanics
Researchers have developed novel graph neural network (GNN) frameworks to accelerate complex physics simulations. One approach, SuperCond-GNN, uses GNNs as a surrogate model to predict voltage distribution in supercondu…
-
New graph neural network improves protein modeling with secondary structure insights
Researchers have developed a new graph neural network model that incorporates secondary structure elements and energy-filtered hydrogen bonds for improved protein representation learning. This approach captures local st…
-
New LUCID method tackles LLM hallucinations in knowledge graph reasoning
Researchers have introduced LUCID, a novel method designed to detect hallucinations in large language models (LLMs) when they are used for knowledge graph reasoning. Unlike previous approaches that focused on LLM intern…
-
New framework Artemis tackles demographic confounders in neuroimaging
Researchers have developed Artemis, a novel region-level causal framework designed to eliminate demographic confounders in multimodal neuroimaging data. This framework integrates functional magnetic resonance imaging (f…
-
New Graph Neural Network Tackles Credit Card Fraud Detection
A new research paper introduces TMR-GGNN, a novel framework for credit card fraud detection that utilizes a time-aware, multi-relational graph neural network. This approach models complex interactions between customers,…
-
New AGDN framework offers improved solutions for Traveling Salesman Problem
Researchers have developed the Anisotropic Graph Diffusion Network (AGDN), a novel Graph Neural Network designed to tackle the Traveling Salesman Problem (TSP). AGDN addresses challenges in exploiting graph structure by…
-
New AI algorithm optimizes mobile network control with graph neural networks
Researchers have developed a novel multi-agent reinforcement learning algorithm called the Temporally Consistent Graph Q-Network (TC-GQN) for optimizing mobile network control. This algorithm learns a task-independent r…