Distilling Large Language Models for Text-Attributed Graph Learning

arXiv:2402.12022v1 Announce Type: cross
Abstract: Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large language models (LLMs) have recently demonstrated remarkable capabilities in few-shot and zero-shot TAG learning, but they suffer from scalability, cost, and privacy issues. Therefore, in this work, we focus on synergizing LLMs and graph models with their complementary strengths by distilling the …

abstract applications arxiv capabilities cs.cl cs.lg documents few-shot graph graph learning graphs human labels language language models large language large language models learn llms tag tags text textual training type zero-shot