MGRAG: Semantic Subgraph Matching and Graph-Aware Caching for Multimodal Retrieval-Augmented Generation
Proceedings of the VLDB Endowment · 01.05.2026 · 19 (9) · 2480-2493
DOI: 10.14778/3819518.3819565 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 19.08.2026. Verfasst von Yubo Wang und 2 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben.
Abstract (Originalsprache)
Answering complex queries over large and heterogeneous multi-modal document corpora is a central challenge in data management, requiring fine-grained, entity-level evidence retrieval and efficient context serving. Graph-based Retrieval-Augmented Generation (RAG) systems achieve promising effectiveness by organizing multimodal documents as knowledge graphs (KGs); however, they still face three limitations: (1) query-agnostic KG construction, where corpus-wide graphs overwhelm query-relevant entities with irrelevant noise; (2) inflexible graph matching, which relies on rigid topological matching and misses path-level semantic equivalences; (3) event-agnostic KV re-computation, which scores tokens independently of graph topology, failing to preserve event-level semantic structure. To address these issues, we propose MGRAG. First, MGRAG incrementally builds query-specific KGs on demand via a lazy, top-down construction strategy. Second, we formulate graph retrieval as a path-based semantic subgraph matching problem, prove it NP-hard, and design an efficient greedy algorithm for flexible, semantics-aware retrieval. Third, MGRAG employs an event-aware KV caching mechanism to selectively recompute tokens critical to query-related events. Experiments on seven real-world multimodal QA datasets show that MGRAG achieves superior effectiveness and efficiency compared to state-of-the-art RAG, subgraph matching, and KV caching baselines.
Zitieren
APA
Wang, Y., Li, H., & Chen, L. (2026). MGRAG: Semantic Subgraph Matching and Graph-Aware Caching for Multimodal Retrieval-Augmented Generation. Proceedings of the VLDB Endowment, 19(9), 2480-2493. https://doi.org/10.14778/3819518.3819565
Vancouver
Wang Y, Li H, Chen L. MGRAG: Semantic Subgraph Matching and Graph-Aware Caching for Multimodal Retrieval-Augmented Generation. Proceedings of the VLDB Endowment. 2026;19(9):2480-2493. doi:10.14778/3819518.3819565
BibTeX
@article{Wang2026,
author = {Wang, Yubo and Li, Haoyang and Chen, Lei},
title = {MGRAG: Semantic Subgraph Matching and Graph-Aware Caching for Multimodal Retrieval-Augmented Generation},
journal = {Proceedings of the VLDB Endowment},
year = {2026},
volume = {19},
number = {9},
pages = {2480--2493},
doi = {10.14778/3819518.3819565}
}
EUVIMED