CADReN: Contextual Anchor-Driven Relational Network for Controllable Cross-Graphs Node Importance Estimation

Autor:	Zhong, Zijie, Zhang, Yunhui, Chang, Ziyi, Qin, Zengchang
Rok vydání:	2024
Předmět:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Information Retrieval 68T07
Druh dokumentu:	Working Paper
Popis:	Node Importance Estimation (NIE) is crucial for integrating external information into Large Language Models through Retriever-Augmented Generation. Traditional methods, focusing on static, single-graph characteristics, lack adaptability to new graphs and user-specific requirements. CADReN, our proposed method, addresses these limitations by introducing a Contextual Anchor (CA) mechanism. This approach enables the network to assess node importance relative to the CA, considering both structural and semantic features within Knowledge Graphs (KGs). Extensive experiments show that CADReN achieves better performance in cross-graph NIE task, with zero-shot prediction ability. CADReN is also proven to match the performance of previous models on single-graph NIE task. Additionally, we introduce and opensource two new datasets, RIC200 and WK1K, specifically designed for cross-graph NIE research, providing a valuable resource for future developments in this domain. Comment: 8 pages, 6 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.05135 Zobrazit plný text záznamu View this record from Arxiv