Leveraging Discrete Semantic Prototypes for Representation Learning on Text-Attributed Graphs

Integrating Large Language Models (LLMs) with Graph Neural Networks (GNNs) has emerged as a dominant paradigm for representation learning on Text-Attributed Graphs (TAGs). Existing approaches face three primary challenges: the difficulty in distinguishing core semantic information from textual redun...

Полное описание

Библиографические подробности

Главные авторы:	Yiming Cao, Cheng Peng, Le-Minh Nguyen
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2026-01-01
Серии:	IEEE Access
Предметы:	Graph representation learning large language model text-attributed graphs vector quantization
Online-ссылка:	https://ieeexplore.ieee.org/document/11373041/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!