An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs

• URL: http://arxiv.org/abs/2603.04545v1
• Date: Wed, 04 Mar 2026 19:30:14 GMT
• Title: An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs
• Authors: Waleed Afandi, Hussein Abdallah, Ashraf Aboulnaga, Essam Mansour,
• Abstract summary: This paper presents KG-WISE, a task-driven inference paradigm for large knowledge graphs (KGs)<n> KG-WISE decomposes trained GNN models into fine-grained components that can be partially loaded based on the structure of the queried subgraph.<n>It achieves up to 28x faster inference and 98% lower memory usage than state-of-the-art systems.
• Score: 4.814637416425641
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference queries are computationally expensive and vary in complexity, as each involves a different number of target nodes linked to subgraphs of diverse densities and structures. Existing acceleration methods, such as pruning, quantization, and knowledge distillation, instantiate smaller models but do not adapt them to the structure or semantics of individual queries. They also store models as monolithic files that must be fully loaded, and miss the opportunity to retrieve only the neighboring nodes and corresponding model components that are semantically relevant to the target nodes. These limitations lead to excessive data loading and redundant computation on large KGs. This paper presents KG-WISE, a task-driven inference paradigm for large KGs. KG-WISE decomposes trained GNN models into fine-grained components that can be partially loaded based on the structure of the queried subgraph. It employs large language models (LLMs) to generate reusable query templates that extract semantically relevant subgraphs for each task, enabling query-aware and compact model instantiation. We evaluate KG-WISE on six large KGs with up to 42 million nodes and 166 million edges. KG-WISE achieves up to 28x faster inference and 98% lower memory usage than state-of-the-art systems while maintaining or improving accuracy across both commercial and open-weight LLMs.

Related papers

• Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching [61.824094419641575]
  Large Language Models (LLMs) struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA)<n>We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures.<n>Existing methods usually employ resource-intensive, non-scalable reasoning on vanilla KGs, but overlook this gap.<n>We propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries.
  arXiv  Detail & Related papers  (2025-09-25T06:48:52Z)
• Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency [59.6772484292295]
  Knowledge graphs (KGs) generated by large language models (LLMs) are increasingly valuable for Retrieval-Augmented Generation (RAG) applications. Existing KG extraction methods rely on prompt-based approaches, which are inefficient for processing large-scale corpora. We propose SynthKG, a multi-step, document-level synthesis KG workflow based on LLMs. We also design a novel graph-based retrieval framework for RAG.
  arXiv  Detail & Related papers  (2024-10-22T00:47:54Z)
• Multi-hop Question Answering over Knowledge Graphs using Large Language Models [1.8130068086063336]
  We evaluate the capability of (LLMs) to answer questions over Knowledge graphs that involve multiple hops. We show that depending upon the size and nature of the KG we need different approaches to extract and feed the relevant information to an LLM.
  arXiv  Detail & Related papers  (2024-04-30T03:31:03Z)
• Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling [5.460112864687281]
  This paper proposes KG-TOSA, an approach to automate the TOSG extraction for task-oriented HGNN training on a large Knowledge Graph (KG) KG-TOSA helps state-of-the-art HGNN methods reduce training time and memory usage by up to 70% while improving the model performance, e.g., accuracy and inference time.
  arXiv  Detail & Related papers  (2024-03-09T01:17:26Z)
• KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph [134.8631016845467]
  We propose an autonomous LLM-based agent framework, called KG-Agent. In KG-Agent, we integrate the LLM, multifunctional toolbox, KG-based executor, and knowledge memory. To guarantee the effectiveness, we leverage program language to formulate the multi-hop reasoning process over the KG.
  arXiv  Detail & Related papers  (2024-02-17T02:07:49Z)
• ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph [142.42275983201978]
  We propose a subgraph-aware self-attention mechanism to imitate the GNN for performing structured reasoning. We also adopt an adaptation tuning strategy to adapt the model parameters with 20,000 subgraphs with synthesized questions. Experiments show that ReasoningLM surpasses state-of-the-art models by a large margin, even with fewer updated parameters and less training data.
  arXiv  Detail & Related papers  (2023-12-30T07:18:54Z)
• KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models [18.20425100517317]
  We propose KG-GPT, a framework leveraging large language models for tasks employing knowledge graphs. KG-GPT comprises three steps: Sentence, Graph Retrieval, and Inference, each aimed at partitioning sentences, retrieving relevant graph components, and deriving logical conclusions. We evaluate KG-GPT using KG-based fact verification and KGQA benchmarks, with the model showing competitive and robust performance, even outperforming several fully-supervised models.
  arXiv  Detail & Related papers  (2023-10-17T12:51:35Z)
• Towards a GML-Enabled Knowledge Graph Platform [0.5904265865319825]
  This vision paper proposes KGNet, an on-demand graph machine learning (GML) as a service on top of RDF engines. KGNet automates the training of GML models on a KG by identifying a task-specific subgraph. All trained models are accessible via a SPARQL-like query.
  arXiv  Detail & Related papers  (2023-03-03T17:41:11Z)
• Logical Message Passing Networks with One-hop Inference on Atomic Formulas [57.47174363091452]
  We propose a framework for complex query answering that decomposes the Knowledge Graph embeddings from neural set operators. On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning. Our approach yields the new state-of-the-art neural CQA model.
  arXiv  Detail & Related papers  (2023-01-21T02:34:06Z)
• Are Message Passing Neural Networks Really Helpful for Knowledge Graph Completion? [49.858038034580005]
  We show that simple models are able to achieve comparable performance to MPNNs. We show careful scoring function and loss function design has a much stronger influence on KGC model performance.
  arXiv  Detail & Related papers  (2022-05-21T18:14:52Z)
• Sequence-to-Sequence Knowledge Graph Completion and Question Answering [8.207403859762044]
  We show that an off-the-shelf encoder-decoder Transformer model can serve as a scalable and versatile KGE model. We achieve this by posing KG link prediction as a sequence-to-sequence task and exchange the triple scoring approach taken by prior KGE methods with autoregressive decoding.
  arXiv  Detail & Related papers  (2022-03-19T13:01:49Z)
• Knowledge Base Question Answering by Case-based Reasoning over Subgraphs [81.22050011503933]
  We show that our model answers queries requiring complex reasoning patterns more effectively than existing KG completion algorithms. The proposed model outperforms or performs competitively with state-of-the-art models on several KBQA benchmarks.
  arXiv  Detail & Related papers  (2022-02-22T01:34:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.