GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs
Researchers have developed GraspLLM, a new framework designed to improve the generalization capabilities of Large Language Models (LLMs) when applied to text-attributed graphs (TAGs). The framework integrates graph structural comprehension with LLM semantic understanding to enhance performance across diverse datasets and tasks, particularly in zero-shot scenarios. GraspLLM achieves this by representing node texts in a unified semantic space, extracting dataset-agnostic structural information through contrastive learning, and aligning relevant subgraphs to the LLM's token space. Experiments show GraspLLM surpasses existing LLM-based methods for TAGs. AI
IMPACT Enhances LLM capabilities for analyzing complex, interconnected data, potentially improving applications in areas like social networks and scientific literature.