Node Classification

2 items

RESEARCHDEV.to AI·12d ago

Graph-MLP: Node Classification without Message Passing in Graph

Graph-MLP introduces a novel approach for node classification in graph neural networks, diverging from traditional message passing mechanisms. This method aims to improve efficiency and performance by classifying nodes directly within the graph structure.

deep learning Graph Neural Networks machine learning Graph-MLP

RESEARCHarXiv CS.LG·19d ago

Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification

This paper introduces Transductive Sharpening (TS), a novel loss-level modification for semi-supervised node classification. It leverages predictions on unlabeled nodes by minimizing prediction entropy to extract useful training signals often discarded by standard supervised objectives.

semi-supervised learning Graph Neural Networks machine learning Node Classification