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

arXiv: https://arxiv.org/abs/2603.04545 · HTML: https://mlsanity.com/paper/2603.04545/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs](https://mlsanity.com/paper/2010.05337/) (2020)
- [Degree-Quant: Quantization-Aware Training for Graph Neural Networks](https://mlsanity.com/paper/2008.05000/) (2020)
- [Decoupling the Depth and Scope of Graph Neural Networks](https://mlsanity.com/paper/2201.07858/) (2022)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [Accelerating Large Scale Real-Time GNN Inference using Channel Pruning](https://mlsanity.com/paper/2105.04528/) (2021)
- [Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding](https://mlsanity.com/paper/2110.14170/) (2021)
- [SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization](https://mlsanity.com/paper/2007.05100/) (2020)
- [Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets](https://mlsanity.com/paper/2103.00794/) (2021)
- [Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks](https://mlsanity.com/paper/2210.13014/) (2022)
- [Anomaly Detection in Dynamic Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2406.00134/) (2024)
- [Influence-Based Mini-Batching for Graph Neural Networks](https://mlsanity.com/paper/2212.09083/) (2022)
- [Edge: Enriching Knowledge Graph Embeddings with External Text](https://mlsanity.com/paper/2104.04909/) (2021)
- [Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling](https://mlsanity.com/paper/2403.05752/) (2024)

## Built on by (most cited first, 2 of 2)

- [GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs](https://mlsanity.com/paper/2606.11898/) (2026)
- [STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling](https://mlsanity.com/paper/2610.00907/) (2026)

## Abstract (arXiv)

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.