graph neural networks ↔ Knowledge Graph

Relations (1)

related 2.00 — strongly supporting 3 facts

Graph neural networks are utilized to process and reason over knowledge graph structures, as evidenced by their role in retrieval frameworks [1] and their ability to calculate node weights for improved interpretability [2]. Furthermore, research explicitly explores the synergy between these two concepts for reasoning tasks [3].

Facts (3)

Sources

Knowledge Graph Combined with Retrieval-Augmented Generation ... drpress.org Academic Journal of Science and Technology 1 fact

referenceThe paper 'Explore then Determine: A GNN-LLM Synergy Framework for Reasoning over Knowledge Graph' by Liu G, Zhang Y, Li Y, et al. was published as an arXiv preprint (arXiv:2406.01145) in 2024.

Empowering GraphRAG with Knowledge Filtering and Integration arxiv.org arXiv 1 fact

referenceGNN-RAG (Mavromatis and Karypis, 2024) leverages Graph Neural Networks (Kipf and Welling, 2016) to process knowledge graph structures for effective retrieval.

Combining Knowledge Graphs and Large Language Models - arXiv arxiv.org arXiv 1 fact

claimGraph neural networks can be used to calculate weights between graph nodes to provide a path of reasoning through a Knowledge Graph, which improves model interpretability.