Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
0 results for “Graph Neural Network”
PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing
A new reinforcement learning algorithm called PPO-STGNN is proposed to improve scheduling of computation-intensive DAG tasks across cloud, edge, and end devices by jointly modeling task dependencies and heterogeneous infrastructure using spatio-temporal graph neural networks and proximal policy optimization.
Sep 4, 2026
Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attribution
A new self-explainable multi-label graph neural network (SEMGNN) is introduced to jointly perform node classification and label-specific edge attribution in multi-label graph learning, addressing a gap in training-time interpretability for correlated labels.
Aug 31, 2026
SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning
A new graph neural network architecture integrates a small language model to dynamically route semantic information in labeled property graphs, improving contextual message propagation while preserving structural integrity.
Aug 28, 2026
From Abductive Explanations to Global Logical Rules for Node Classification in SGCs
A new research paper introduces a logic-based framework that extracts compact, globally applicable logical rules from Simple Graph Convolution (SGC) models by using minimal abductive explanations as an intermediate step, aiming to improve explainability without sacrificing fidelity.
Aug 19, 2026
Exploring Oversmoothing with Householder Matrices
A new graph neural network architecture called HouseGNN is proposed to mitigate oversmoothing in deep GNNs by using Householder reflectors and GroupSort to preserve node-wise Euclidean norms across layers.
Aug 14, 2026
Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
A new arXiv preprint (2607.09666v1) publishes a comprehensive, taxonomy-driven survey of Graph Neural Network (GNN) applications across the full knowledge graph (KG) technology lifecycle — from construction to reasoning to applications — identifying gaps, strengths, limitations, and future research directions.
Jul 14, 2026
PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation
A new AI research paper proposes PRecG, a graph-based method for legal precedent retrieval that segments judgments by rhetorical role and builds knowledge graphs per segment to improve semantic matching.
Jul 13, 2026