Joint Structure-Label Estimation vs. Mini-Batch Training in Low-Label Graph Neural Networks

This report synthesises findings from 15 peer-reviewed papers addressing the following research question: How does the convergence speed and final accuracy of joint structure-label estimation in graph neural networks compare to mini-batch training when evaluated on the Cora, Citeseer, and PubMed. Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the Data Augmentation training strategy can aid in its development. 7 claims were extracted from source literature; 7 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the convergence speed and final accuracy of joint structure-label estimation in graph neural networks compare to mini-batch training when evaluated on the Cora, Citeseer, and PubMed benchmarks in a low-label regime?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.