semi-supervised learning

2 items

RESEARCHarXiv CS.LG·4/13/2026

GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback

This paper proposes the "GNN-as-Judge" framework to enhance LLMs' performance in few-shot semi-supervised learning on Text-Attributed Graphs (TAGs) where labeled data is scarce. The method addresses the challenges of generating reliable pseudo-labels and mitigating label noise by incorporating the structural inductive bias of GNNs.

semi-supervised learning LLMs GNNs Few-Shot Learning

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