graph neural network
PulseAugur coverage of graph neural network — every cluster mentioning graph neural network across labs, papers, and developer communities, ranked by signal.
16 day(s) with sentiment data
-
AI framework learns altruistic robot allocation using ecological principles
Researchers have developed a new framework for multi-team collaboration in systems with heterogeneous capabilities, treating robots as transferable resources. This approach utilizes Hamilton's rule from ecology to guide…
-
New theory guarantees success for AI model distillation in optimization
Researchers have developed a theoretical framework for successful knowledge distillation in combinatorial optimization tasks. Their work focuses on scenarios where a smaller Graph Neural Network (GNN) is trained to mimi…
-
Robots use AI planner and controller for complex motion tasks
Researchers have developed a new hierarchical framework for multi-robot motion planning that combines a Graph Attention Planner (GATP) with a decentralized Nonlinear Model Predictive Controller (NMPC). This approach add…
-
AI Oracle predicts Taiwan Strait conflict and GNN dominance
Synthetica Oracle, an AI agent, has issued two predictions regarding future trends. One forecast highlights the Taiwan Strait as a high-risk conflict zone due to US-China tensions. The other prediction anticipates Graph…
-
SAGE3D model enhances 3D LiDAR corner detection with novel attention
Researchers have introduced SAGE3D, a novel Transformer-based model designed for detecting corners in 3D point clouds from LiDAR data. The model employs a hierarchical encoder-decoder architecture and incorporates two k…
-
NHN launches 7,656-GPU cluster; Hermes Agent hits 140K stars; new AI bias framework
NHN has launched a substantial 7,656-GPU cluster in Seoul, South Korea, aimed at domestic enterprise AI workloads, positioning itself against competitors like Naver and Kakao. Meanwhile, the Hermes Agent project has sur…
-
ML model integrates patient data and esophageal graphs for disorder classification
Researchers have developed a multimodal machine learning approach to classify esophageal motility disorders by integrating high-resolution impedance manometry (HRIM) data with patient-specific information. This method u…
-
AI model trained on 120M physics events improves collision data classification
Researchers have developed a new foundation model for event classification in high-energy physics, utilizing a Graph Neural Network architecture. This model was pretrained on 120 million simulated proton-proton collisio…
-
ReMAP framework offers scalable MAP inference for arbitrary-order MRFs
Researchers have developed ReMAP, a novel framework for scalable Markov Random Field (MRF) inference. This method utilizes a Graph Neural Network to optimize a differentiable relaxation of the MRF energy, enabling gradi…
-
New framework tests GSSL robustness on noisy biomedical graphs
Researchers have introduced a new framework, NATD-GSSL, to evaluate and improve the robustness of Graph Self-Supervised Learning (GSSL) methods when applied to noisy, text-derived graphs. Existing GSSL techniques typica…
-
Neural networks possess finite sample complexity, paper shows
A new paper demonstrates that a wide range of feedforward neural network architectures possess finite sample complexity. This means they can learn effectively in the PAC model, even with unbounded parameters. The findin…
-
New research framework links neural encoder geometry to graph matching accuracy
Researchers have developed a theoretical framework to understand how the geometry of encoders impacts the quality of neural graph matching, specifically for approximating Graph Edit Distance (GED). Their work connects e…
-
Topological deep learning models struggle to generalize beyond data structure
Researchers have introduced a new evaluation protocol for topological deep learning models, extending the MANTRA benchmark with more diverse manifold triangulations. Their findings indicate that while graph neural netwo…
-
Federated GNNs sync embeddings to detect subgraph patterns across clients
Researchers have developed a novel framework for federated subgraph pattern detection, addressing the challenge of decentralized graph data. Their approach involves a per-step, layer-wise exchange of intermediate node r…
-
New research analyzes full-graph vs. mini-batch GNN training
This paper presents a comprehensive analysis comparing full-graph and mini-batch training for Graph Neural Networks (GNNs). It explores the impact of batch size and fan-out size on GNN convergence and generalization, of…
-
New attack reconstructs private graph data from GNN explanations
Researchers have developed a new attack called PRIVX that can reconstruct hidden graph structures from differentially private Graph Neural Network (GNN) explanations. The attack exploits the Gaussian differential privac…
-
GNN analysis shows EU carbon mechanism shifts electricity prices
This paper introduces a Graph Neural Network (GNN) framework to analyze the impact of the European Union's Carbon Border Adjustment Mechanism (CBAM) on electricity prices and carbon intensity. The study models a subgrap…
-
AI simulates VC collective decision-making to predict startup success
Researchers have developed a new collective agent system called SimVC-CAS to predict startup success by simulating venture capital decision-making as a multi-agent interaction process. This system utilizes role-playing …
-
GEM framework boosts dialogue state tracking with graph-enhanced experts and ReAct agents
Researchers have developed GEM, a novel framework for Dialogue State Tracking that combines graph-enhanced mixture-of-experts with ReAct agents. This approach dynamically routes between specialized experts, including a …
-
Graph Neural Networks Enhance Quantum Architecture Search and Wireless Systems
Researchers have developed a novel Graph Neural Network (GNN) approach for optimizing spectral and energy efficiency in multi-base station systems with reconfigurable intelligent surfaces. Separately, a new magic-inform…