Large Language Model

GNNs as Adapters for LLMs on Text-Attributed Graphs
In this work, we propose GraphAdapter to harness the power of the LLM without fine-tuning its weights on Text-Attributed Graphs. Given a TAG, an adapter GNN is trained to reduce the LLM’s error in predicting the next word of text sequences on nodes.
Xuanwen Huang, Kaiqiao Han, Yang Yang, 包德政, Quanjin Tao, Ziwei Chai, Qi Zhu
PDF Cite Code Yang Yang Xuanwen Huang
GNNs as Adapters for LLMs on Text-Attributed Graphs