Graph-Based Retrieval-Augmented Generation for Multi-Hop Reasoning over Heterogeneous Knowledge Graphs
Keywords:
graph-based retrieval-augmented generation, heterogeneous knowledge graphs, multi-hop reasoning, knowledge graph retrieval, socio-technical systems, governance, robustness, fairness, sustainable infrastructureAbstract
Graph-based retrieval-augmented generation has emerged as a promising approach for grounding large language models in structured evidence, yet multi-hop reasoning over heterogeneous knowledge graphs remains difficult because entities, relations, schemas, and provenance differ across sources. This paper examines graph-based retrieval-augmented generation as a socio-technical infrastructure rather than a single model component. It analyzes how heterogeneous graph construction, semantic alignment, subgraph retrieval, attention-based fusion, and constrained generation interact with latency, scalability, auditability, fairness, and sustainability. The discussion highlights trade-offs between depth of reasoning and operational cost, between recall and precision in evidence selection, and between centralized governance and federated autonomy. It also considers deployment in cloud, edge, and hybrid environments, where graph stores, vector indexes, caches, and policy engines must be coordinated. The paper argues that robust multi-hop reasoning depends less on any single retrieval or generation mechanism than on end-to-end architecture: provenance-preserving data pipelines, calibrated retrieval policies, interpretable path selection, and governance that assigns accountability across institutions. Cross-domain comparisons from enterprise knowledge management, biomedical discovery, public-sector decision support, and scientific literature synthesis show that heterogeneous graphs introduce both richer reasoning opportunities and greater failure modes. The paper concludes with a research agenda for evaluation, fairness auditing, resilience, and sustainable operation.
References
1. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
2. Karpukhin, V., Oğuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W. (2020). Dense passage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 6769–6781.
3. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M. (2020). Retrieval augmented language model pre-training. Proceedings of the 37th International Conference on Machine Learning, 3929–3938.
4. Izacard, G., & Grave, E. (2021). Leveraging passage retrieval with generative models for open domain question answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 874–880.
5. Deng, Q., Liu, S., Qiu, H., Long, N., Lin, W., & Chen, S. (2026, April). Unified Semantic Space and Attention-Based Fusion Framework for Multi-Source Heterogeneous Retrieval-Augmented Generation. In 2026 6th International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) (pp. 591-597). IEEE.
6. Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J. B., Damoc, B., Clark, A., de Las Casas, D., Guy, A., Menick, J., Ring, R., Hennigan, T., Huang, S., Maggiore, L., Jones, C., Cassirer, A., Brock, A., Paganini, M., Irving, G., Vinyals, O., Osindero, S., Simonyan, K., Rae, J. W., Elsen, E., & Sifre, L. (2022). Improving language models by retrieving from trillions of tokens. Proceedings of the 39th International Conference on Machine Learning, 2206–2240.
7. Yasunaga, M., Ren, H., Bosselut, A., Liang, P., & Leskovec, J. (2021). QA-GNN: Reasoning with language models and knowledge graphs for question answering. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 535–546.
8. Lin, B. Y., Chen, X., Chen, J., & Ren, X. (2019). KagNet: Knowledge-aware graph networks for commonsense reasoning. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2829–2839.
9. Feng, Y., Chen, X., Lin, B. Y., Wang, P., Chang, J., & Ren, X. (2020). Scalable multi-hop relational reasoning for knowledge-aware question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 1295–1309.
10. Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2021). A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Transactions on Neural Networks and Learning Systems, 33(2), 494–514.
11. Hogan, A., Blomqvist, E., Cochez, M., d’Amato, C., de Melo, G., Gutiérrez, C., Kirrane, S., Labra Gayo, J. E., Navigli, R., Ngomo, A. C. N., Polleres, A., Rashid, S. M., Rula, A., Schmelzeisen, L., Sequeda, J., Staab, S., & Zimmermann, A. (2021). Knowledge graphs. ACM Computing Surveys, 54(4), 1–37.
12. Bordes, A., Usunier, N., Garcia-Durán, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. Advances in Neural Information Processing Systems, 26, 2787–2795.
13. Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018). Modeling relational data with graph convolutional networks. The Semantic Web: 15th International Conference, ESWC 2018, 593–607.
14. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. International Conference on Learning Representations.
15. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. International Conference on Learning Representations.
16. Hamilton, W. L., Ying, R., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30, 1024–1034.
17. Sun, Z., Deng, Z. H., Nie, J. Y., & Tang, J. (2019). RotatE: Knowledge graph embedding by relational rotation in complex space. International Conference on Learning Representations.
18. Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., & Larson, J. (2024). From local to global: A graph RAG approach to query-focused summarization. arXiv preprint arXiv:2404.16130.
19. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.
20. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2024). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. International Conference on Learning Representations.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Data Intelligence and AI Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
