FastInsight: Fast and Insightful Retrieval via Fusion Operators for Graph RAG
This work addresses the efficiency bottleneck in Graph RAG for retrieval tasks, offering a domain-specific improvement.
The paper tackled the problem of time-intensive insightful retrieval in Graph RAG methods by proposing FastInsight, which uses novel fusion operators to improve retrieval accuracy and generation quality, achieving a substantial Pareto improvement in effectiveness and efficiency.
Existing Graph RAG methods aiming for insightful retrieval on corpus graphs typically rely on time-intensive processes that interleave Large Language Model (LLM) reasoning. To enable time-efficient insightful retrieval, we propose FastInsight. We first introduce a graph retrieval taxonomy that categorizes existing methods into three fundamental operations: vector search, graph search, and model-based search. Through this taxonomy, we identify two critical limitations in current approaches: the topology-blindness of model-based search and the semantics-blindness of graph search. FastInsight overcomes these limitations by interleaving two novel fusion operators: the Graph-based Reranker (GRanker), which functions as a graph model-based search, and Semantic-Topological eXpansion (STeX), which operates as a vector-graph search. Extensive experiments on broad retrieval and generation datasets demonstrate that FastInsight significantly improves both retrieval accuracy and generation quality compared to state-of-the-art baselines, achieving a substantial Pareto improvement in the trade-off between effectiveness and efficiency.