DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation

2026-02-09

AI Summary

Existing graph-based retrieval-augmented generation (G-RAG) methods underutilize graph topology and struggle with dynamically complex queries. This work proposes the first integration of dynamic attributed community search (ACS) into the RAG framework, enabling query-driven extraction of high-order subgraphs and self-completing knowledge retrieval. By leveraging a block-level guided graph indexing strategy, the approach achieves multi-granular and efficient retrieval. The method substantially improves retrieval quality, yielding up to a 40% gain across four key metrics, while simultaneously reducing index construction time by 37% and token consumption by 41%, thereby achieving a favorable balance between performance and cost efficiency.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Distributed Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Owing to their unprecedented comprehension capabilities, large language models (LLMs) have become indispensable components of modern web search engines. From a technical perspective, this integration represents retrieval-augmented generation (RAG), which enhances LLMs by grounding them in external knowledge bases. A prevalent technical approach in this context is graph-based RAG (G-RAG). However, current G-RAG methodologies frequently underutilize graph topology, predominantly focusing on low-order structures or pre-computed static communities. This limitation affects their effectiveness in addressing dynamic and complex queries. Thus, we propose DA-RAG, which leverages attributed community search (ACS) to extract relevant subgraphs based on the queried question dynamically. DA-RAG captures high-order graph structures, allowing for the retrieval of self-complementary knowledge. Furthermore, DA-RAG is equipped with a chunk-layer oriented graph index, which facilitates efficient multi-granularity retrieval while significantly reducing both computational and economic costs. We evaluate DA-RAG on multiple datasets, demonstrating that it outperforms existing RAG methods by up to 40% in head-to-head comparisons across four metrics while reducing index construction time and token overhead by up to 37% and 41%, respectively.

Problem

• Retrieval-Augmented Generation
• Graph-based RAG
• Dynamic Query
• Graph Topology
• Attributed Community Search

Innovation

• Dynamic Attributed Community Search
• Retrieval-Augmented Generation
• Graph-based RAG
• High-order Graph Structures
• Multi-granularity Retrieval