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

TL;DR

DA-RAG introduces a dynamic attributed community search method for retrieval-augmented generation, capturing complex graph structures and improving retrieval efficiency and effectiveness in large language model applications.

Contribution

It presents a novel dynamic attributed community search approach with a chunk-layer graph index, enhancing retrieval of complex graph structures for RAG tasks.

Findings

Outperforms existing RAG methods by up to 40% across four metrics.

Reduces index construction time by up to 37%.

Decreases token overhead by up to 41%.

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.