CADReN: Contextual Anchor-Driven Relational Network for Controllable Cross-Graphs Node Importance Estimation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909098754179072 |
|---|---|
| author | Zhong, Zijie Zhang, Yunhui Chang, Ziyi Qin, Zengchang |
| author_facet | Zhong, Zijie Zhang, Yunhui Chang, Ziyi Qin, Zengchang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05135 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CADReN: Contextual Anchor-Driven Relational Network for Controllable Cross-Graphs Node Importance Estimation Zhong, Zijie Zhang, Yunhui Chang, Ziyi Qin, Zengchang Artificial Intelligence Computation and Language Information Retrieval 68T07 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. |
| title | CADReN: Contextual Anchor-Driven Relational Network for Controllable Cross-Graphs Node Importance Estimation |
| topic | Artificial Intelligence Computation and Language Information Retrieval 68T07 |
| url | https://arxiv.org/abs/2402.05135 |