Skip to main content

Graph Neural Networks

RAGraph: A General Retrieval-Augmented Graph Learning Framework
·2459 words·12 mins· loading · loading
AI Generated Machine Learning Graph Neural Networks 🏢 Peking University
RAGRAPH, a novel retrieval-augmented graph learning framework, boosts GNN generalization by integrating external graph data, significantly outperforming state-of-the-art methods.
Non-convolutional graph neural networks.
·2234 words·11 mins· loading · loading
Graph Neural Networks 🏢 New York University
RUM neural network, a novel non-convolutional GNN, overcomes limitations of conventional convolution-based models by using RNNs to merge topological and semantic features along random walks, achieving…
Graph Coarsening with Message-Passing Guarantees
·2006 words·10 mins· loading · loading
Machine Learning Graph Neural Networks 🏢 IRISA, Rennes, France
This paper introduces a new message-passing operation for coarsened graphs with theoretical guarantees, improving GNN efficiency and accuracy on large datasets.