DynaGRAG | 探索信息拓扑以推进图检索增强生成中的语言理解与生成
DynaGRAG | Exploring the Topology of Information for Advancing Language Understanding and Generation in Graph Retrieval-Augmented Generation
AI总结：
提出DynaGRAG框架，通过去重、两步均值池化、查询感知检索及DSA-BFS算法增强知识图谱子图表示与多样性，结合GCN与LLM提升语言理解与生成能力。
摘要：
图检索增强生成（GRAG或Graph RAG）架构旨在通过利用外部知识来增强语言理解与生成。然而，有效捕获和整合文本与结构化数据中丰富的语义信息仍是一项挑战。为解决此问题，提出了一种新颖的GRAG框架——动态图检索增强生成（DynaGRAG），专注于增强知识图谱内的子图表示与多样性。通过提高图密度、更有效地捕获实体与关系信息，并动态优先处理相关且多样的子图及其内部信息，该方法能够更全面地理解底层语义结构。这通过结合去重过程、嵌入的两步均值池化、考虑唯一节点的查询感知检索，以及动态相似性感知BFS（DSA-BFS）遍历算法来实现。通过硬提示将图卷积网络（GCNs）与大语言模型（LLMs）集成，进一步增强了丰富节点与边表示的学习，同时保留了层次化子图结构。实验结果证明了DynaGRAG的有效性，展示了增强子图表示与多样性对于改善语言理解与生成的重要意义。
英文摘要：
Graph Retrieval-Augmented Generation (GRAG or Graph RAG) architectures aim to enhance language understanding and generation by leveraging external knowledge. However, effectively capturing and integrating the rich semantic information present in textual and structured data remains a challenge. To address this, a novel GRAG framework, Dynamic Graph Retrieval-Agumented Generation (DynaGRAG), is proposed to focus on enhancing subgraph representation and diversity within the knowledge graph. By improving graph density, capturing entity and relation information more effectively, and dynamically prioritizing relevant and diverse subgraphs and information within them, the proposed approach enables a more comprehensive understanding of the underlying semantic structure. This is achieved through a combination of de-duplication processes, two-step mean pooling of embeddings, query-aware retrieval considering unique nodes, and a Dynamic Similarity-Aware BFS (DSA-BFS) traversal algorithm. Integrating Graph Convolutional Networks (GCNs) and Large Language Models (LLMs) through hard prompting further enhances the learning of rich node and edge representations while preserving the hierarchical subgraph structure. Experimental results demonstrate the effectiveness of DynaGRAG, showcasing the significance of enhanced subgraph representation and diversity for improved language understanding and generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
