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

  • 类型:arxiv
  • 标识:2607.00052
  • 链接:https://arxiv.org/abs/2607.00052
  • 主分类:rag
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:AGE focuses on predicting nodes apart from key nodes, utilizing a learnable node sampler, and significantly improves approaches using non-parametric search component in GraphQA tasks, achieving superior accuracy across four benchmark datasets with distinct characteristics.
  • OpenAlex ID:W7167091014
  • OpenAlex DOI:10.48550/arxiv.2607.00052
  • DOI:10.48550/arxiv.2607.00052
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.00052
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:AGE:面向图检索增强生成中图嵌入的自适应掩码方法
  • TLDR中文:AGE 专注于预测关键节点以外的节点,采用可学习节点采样器,在基于非参数检索组件的 GraphQA 任务上取得显著提升,在四个具有不同特征的基准数据集上均达到更高的准确率。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-06-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]