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 graph convolutional network 90%
- instance of machine learning 90%
- used by knowledge graph 90%
- used by CatalyzeX 70%
- instance of ScienceCast 70%
- uses large-language models 70%
- used by ScienceCast 70%
- used by Gotit.pub 70%
- instance of DagsHub 70%
- used by Transformer++ 70%
18 day(s) with sentiment data
-
New GNN encoder enables transferable models for graph optimization tasks
Researchers have developed a new graph neural network (GNN) encoder that utilizes a GCON module for expressive message passing and energy-based unsupervised loss functions. This model demonstrates competitive performanc…
-
ProTAGAD model tackles anomaly detection in text-attributed graphs
Researchers have developed ProTAGAD, a novel foundation model designed for anomaly detection in Text-Attributed Graphs (TAGs). This model addresses the challenge of jointly analyzing topological structures and textual s…
-
New molecular LLM uses substructure rationale for improved property prediction
Researchers have developed MR-MoL, a novel molecular large language model (LLM) designed for property prediction in drug discovery. Unlike existing models that represent molecules implicitly, MR-MoL explicitly incorpora…
-
New methods tackle LLM and VLM hallucinations with internal analysis · 2 sources tracked
Researchers have developed new methods to detect hallucinations in large language and vision-language models. UniProbe, a technique for Large VLMs, uses a graph neural network, a Vision Transformer, and a gated recurren…
-
ML approach optimizes energy scheduling for satellite-to-device power transfer
Researchers have developed a novel machine learning-based approach for energy scheduling in dynamic Non-Terrestrial Network-Wireless Power Transfer (NTN-WPT) systems. This method aims to optimize energy efficiency, task…
-
Graph learning framework tackles transformer circuit localization
Researchers have introduced Graph Circuit Learning (GCL), a novel framework that treats circuit localization in transformer models as a graph machine learning problem. This approach trains a graph neural network (GNN) a…
-
New GNN Framework Diagnoses Component-Level Anomalies in Industrial Systems
Researchers have developed a new framework using Graph Neural Networks (GNNs) to diagnose anomalies in complex industrial systems. Unlike previous methods that focus on individual sensor deviations, this approach identi…
-
New GNN-GA algorithm optimizes Physical Internet supply chains
Researchers have developed a novel Graph Neural Network--Guided Genetic Algorithm (GNN-GA) to optimize complex supply chain networks within the Physical Internet framework. This approach combines discrete assignment dec…
-
SmartNICs accelerate large-scale GNN training by reducing communication overhead · 2 sources tracked
Two new research papers propose methods to accelerate large-scale graph neural network (GNN) training by offloading tasks to SmartNICs. LGNNIC focuses on reducing communication overhead by performing neighbor sampling a…
-
BDD2Seq framework enhances reversible-circuit synthesis for quantum computing
Researchers have developed BDD2Seq, a novel graph-to-sequence framework designed to improve reversible-circuit synthesis for quantum computing. This approach utilizes a Graph Neural Network encoder and a Pointer-Network…
-
New PriDyG framework enhances privacy in dynamic graph inference using LLM-GNN collaboration
Researchers have developed PriDyG, a novel framework for privacy-preserving dynamic graph inference. This system combines graph neural networks (GNNs) with large language models (LLMs) to protect sensitive edge informat…
-
New framework enhances LLM reasoning over incomplete knowledge graphs
Researchers have developed a novel graph-based soft prompting framework to improve the reasoning capabilities of large language models (LLMs) when dealing with incomplete knowledge graphs. This approach shifts the focus…
-
New HINet Model Estimates Treatment Effects in Networks Without Predefined Exposure Mappings
Researchers have developed HINet, a novel neural network approach designed to estimate treatment effects in network settings where interference between nodes is a factor. Unlike previous methods that require a predefine…
-
Survey paper details fairness challenges in augmented graph learning
A new survey paper, "Fairness in Augmented Graph Learning: A Survey," explores the unique fairness challenges introduced by integrating specialized machine learning techniques into graph learning. The paper, termed Fair…
-
New CReSL method enhances Graph Domain Adaptation by modeling resolution shifts
Researchers have introduced Cross-Resolution Semantic Learning (CReSL), a novel method for Graph Domain Adaptation (GDA). CReSL addresses the challenge of transferring knowledge between graphs with differing neighborhoo…
-
New MPP-GNN model advances Alzheimer's classification using fMRI data
Researchers have developed a new graph neural network model called MPP-GNN for analyzing functional magnetic resonance imaging (fMRI) data to classify Alzheimer's disease. This model addresses limitations in existing me…
-
Graph Neural Networks Advance Spin Dynamics Simulations in Metallic Magnets
Researchers have developed a novel graph neural network (GNN) framework designed to predict the effective magnetic energy functional for metallic magnets. This approach bypasses the computationally intensive process of …
-
New FICE model offers fully inductive cardinality estimation for knowledge graphs
Researchers have developed FICE, a novel graph neural network designed for fully inductive cardinality estimation in SPARQL queries over knowledge graphs. Unlike previous methods that require retraining for new or modif…
-
Graph Signal Diffusion Models optimize wireless resource allocation
Researchers have developed Graph Signal Diffusion Models (GSDMs) to optimize resource allocation in wireless networks with graph-structured interference. These models leverage a U-Net architecture composed of graph neur…
-
Graph Neural Network Solves Word Problem for Cryptographic Applications
Researchers have developed WPNet, a novel Graph Neural Network designed to heuristically solve the Word Problem for certain non-abelian groups. This model maps unreduced words to dynamic graph structures, clustering alg…