Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs

arXiv:2310.18152v4 Announce Type: replace-cross
Abstract: Text-attributed graphs (TAGs) are prevalent on the web and research over TAGs such as citation networks, e-commerce networks and social networks has attracted considerable attention in the web community. Recently, large language models (LLMs) have demonstrated exceptional capabilities across a wide range of tasks. However, the existing works focus on harnessing the potential of LLMs solely relying on prompts to convey graph structure information to LLMs, thus suffering from insufficient understanding of the complex structural …

abstract arxiv attention capabilities commerce community cs.cl cs.lg e-commerce graphs however language language models large language large language models llms networks representation representation learning research social social networks tags tasks text type web