mlsanityData to 14 Oct 2026

DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systems

arXiv 2505.19847 ↗First posted 26 May 2025cs.AI cs.DCcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external knowledge, yet conventional centralized RAG requires aggregating distributed data, raising privacy risks and incurring high retrieval latency and cost. We present DGRAG, a distributed graph-driven RAG framework for edge-cloud collaborative systems. Each edge device organizes local documents into a knowledge graph and periodically uploads subgraph-level summaries to the cloud for lightweight global indexing without exposing raw data. At inference time, queries are first answered on the edge; a gate mechanism assesses the confidence and consistency of multiple local generations to decide whether to return a local answer or escalate the query. For escalated queries, the cloud performs summary-based matching to identify relevant edges, retrieves supporting evidence from them, and generates the final response with a cloud LLM. Experiments on distributed question answering show that DGRAG consistently outperforms decentralized baselines while substantially reducing cloud overhead.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 45 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

30 of 45 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance15 Apr
  2. 2024EdgeRAG: Online-Indexed RAG for Edge Devices30 Dec
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  4. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation28 Sep

Other references · 26

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2023Qwen Technical Reportcited by 3,344
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  9. 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 385
  10. 2023A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPTcited by 368
  11. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  12. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
14 more
  1. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  2. 2022RealTime QA: What's the Answer Right Now?cited by 244
  3. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  4. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  5. 2024LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domaincited by 118
  6. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
  7. 2024GRAG: Graph Retrieval-Augmented Generationcited by 78
  8. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 61
  9. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
  10. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 26
  11. 2024Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selectioncited by 25
  12. 2024C-FedRAG: A Confidential Federated Retrieval-Augmented Generation Systemcited by 19
  13. 2025AVA: Towards Agentic Video Analytics with Vision Language Modelscited by 5
  14. 2025Distributed Retrieval-Augmented Generationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CoEdge-RAG: Optimizing Hierarchical Scheduling for Retrieval-Augmented LLMs in Collaborative Edge Computing
  2. 2026From Cloud to Crowd: Democratizing LLM Service with Decentralized Edge Collaboration for RAG ↗
  3. 2024EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update
  4. 2026CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation
  5. 2024EdgeShard: Efficient LLM Inference via Collaborative Edge Computing
  6. 2024SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
  7. 2025Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges
  8. 2025HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Data