AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

GraphRAG extends RAG by incorporating graph-structured data for LLMs, addressing latent feature misalignment through Adaptive-masking for Graph Embedding (AGE) that uses Transforme…

Hugging Face · Daily Papers ·Bao Long Nguyen Huu, Atsushi Hashimoto · ·▲ 3 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Bao Long Nguyen Huu, Atsushi Hashimoto

  • 3 upvotes da comunidade
  • Temas: retrieval-augmented generation, large language models, graph-structured data, latent feature misalignment, Transformer, self-supervised learning

Resumo

Resumo original (em inglês), extraído do paper:

GraphRAG extends RAG by incorporating graph-structured data for LLMs, addressing latent feature misalignment through Adaptive-masking for Graph Embedding (AGE) that uses Transformer-based self-supervised learning with learnable node sampling.

Onde ler

compartilhar: