GraphGPT: Graph Instruction Tuning for Large Language Models

arXiv:2310.13023v3 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods often depend on fine-tuning with task-specific labels, limiting their effectiveness when labeled data is scarce. Our research tackles this by advancing graph model generalization in zero-shot learning environments. Inspired by the success of large language models (LLMs), we aim to create a …

arxiv cs.ai cs.cl graph instruction tuning language language models large language large language models type