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 alphaXiv 90%
- instance of Gotit.pub 90%
- instance of machine learning 90%
- used by knowledge graph 90%
- used by DagsHub 70%
- used by alphaXiv 70%
- used by ScienceCast 70%
- used by Gotit.pub 70%
- instance of CatalyzeX 70%
- used by CatalyzeX 70%
- instance of ScienceCast 70%
- uses large-language models 70%
15 day(s) with sentiment data
-
JointMatch integrates ride-sharing matching with graph neural networks
Researchers have developed JointMatch, a novel framework that unifies ride-sharing matching problems into a single graph neural network solver. This approach addresses the limitations of traditional sequential methods b…
-
MetaRTL framework enhances relational table learning with meta-path attention
Researchers have introduced MetaRTL, a novel two-stage framework designed to improve relational table learning, particularly for large real-world databases. This method utilizes lightweight pre-training for initial tabl…
-
New HP method enhances stability in graph neural network evaluations
Researchers have developed a new method called HP, or Homophily-Aware Stratification, to improve the reliability of graph neural network (GNN) evaluations. Traditional random splitting of data for GNN training and testi…
-
Graph Neural Network Model Predicts Individual Network Traffic Flows
Researchers have developed a Graph Neural Network (GNN) model capable of predicting network traffic at the individual flow level (NetFlow). This model effectively captures the graph structure and connection features wit…
-
FoundAna: New GNN-Transformer Model for Generalizable Graph Anomaly Detection
Researchers have introduced FoundAna, a novel foundation model designed for generalizable graph anomaly detection. This model combines graph neural networks (GNNs) with a transformer architecture, enhanced by four types…
-
New stable filters enhance generative models for graph signals
Researchers have developed a new framework for designing stable graph filters to improve generative models for graph signals. These filters are designed to preserve the smoothing properties of graph heat diffusion while…
-
New framework MAGER uses genetic evolution to improve LLM fake news detection
Researchers have developed MAGER, a novel multi-agent genetic evolution framework designed to enhance fake news detection using large language models (LLMs). This framework addresses the challenges of modality mismatch …
-
New framework ReDIL-GNN tackles domain shift in circuit GNNs
Researchers have introduced ReDIL-GNN, a novel framework designed to address domain shift in circuit graph neural networks (GNNs) that arises from logic resynthesis. This framework enables GNNs to adapt to new synthesis…
-
New EV-GNN accelerator achieves 25μs latency for edge AI
Researchers have developed ETHEREAL, a novel event-driven graph neural network (EV-GNN) accelerator designed for ultra-low-latency AI processing at the edge. This system addresses the challenges of processing data from …
-
New VBLL method enhances online node classification on evolving graphs
Researchers have developed a new method called variational Bayesian last-layer (VBLL) for online node classification on evolving graphs. This approach addresses the challenges of inductive generalization and calibrated …
-
GPEvac: AI framework generates adaptive evacuation routes in milliseconds
Researchers have developed GPEvac, a novel framework utilizing graph neural networks and Proximal Policy Optimization to create adaptive evacuation routes during shooting events. This system aims to minimize threat expo…
-
New AI frameworks enhance cloud scheduling efficiency and resource management · 3 sources tracked
Researchers have developed advanced reinforcement learning frameworks to optimize cloud workflow scheduling. The first approach, GA-HRL, uses a Graph Attention Network to model task dependencies and a hierarchical semi-…
-
New GNN framework optimizes quantum circuit scheduling for multi-QPU systems
Researchers have developed a new framework for scheduling quantum circuits on multi-QPU systems, aiming to maximize execution fidelity. This system utilizes a Graph Neural Network (GNN) to estimate the expected fidelity…
-
Research compares automatic differentiation and discretization for AI-powered PDE solvers
A new research paper systematically analyzes the trade-offs between automatic differentiation (AD) and discretization-based constraints for physics-informed neural networks (PINNs) used in solving partial differential e…
-
New VERITAS protocol enhances privacy and security in graph learning
Researchers have introduced VERITAS, a new protocol designed to enhance the security and privacy of graph learning systems. VERITAS addresses the vulnerability of locally private graph learning protocols to data poisoni…
-
GraphNOSE: New Graph Transformer Predicts Olfactory Qualities
Researchers have developed GraphNOSE, an open-source graph transformer framework designed to predict olfactory qualities from molecular structures. This new model demonstrates superior performance compared to existing l…
-
New method uses Instance Graphs and GNNs for better process prediction
Researchers have developed a new approach for next activity prediction in processes by utilizing Instance Graphs and Graph Neural Networks. This method explicitly encodes contextual information, such as environmental co…
-
New AI system TeethGNN automates malocclusion grading from CBCT scans
Researchers have developed TeethGNN, a novel graph-based framework for automatically grading malocclusion from cone-beam computed tomography (CBCT) images. This system bypasses the need for manual measurements by direct…
-
New framework generates synthetic logistics demand data with 16% improvement
Researchers have developed a new framework for generating synthetic origin-destination demand data in logistics networks. This constraint-aware generative model can produce demand patterns that adapt to changes in netwo…
-
New WEECFP-SuRGE architecture shows strong performance on molecular property prediction
Researchers have developed WEECFP-SuRGE, a novel transformer architecture that utilizes a unique graph-distance encoding method for molecular fingerprints. This approach, which encodes substructures within vectors and u…