KGCompiler: Deep Learning Compilation Optimization for Knowledge Graph Complex Logical Query Answering

2025-03-04

AI Summary

To address the escalating inference latency and memory overhead in Complex Logical Query Answering (CLQA) over knowledge graphs—particularly as the number of first-order logic (FOL) operators increases—this paper introduces KGCompiler, the first deep learning compiler tailored for CLQA. Methodologically, KGCompiler establishes a knowledge-graph–specific compilation and optimization paradigm, enabling cross-algorithm, non-intrusive, end-to-end optimization. It integrates KG semantics–aware graph-structure scheduling with an FOL operator–level intermediate representation (IR), facilitating tensor fusion and memory reuse. Evaluated on multiple CLQA benchmarks, KGCompiler achieves 1.04×–8.26× speedup (average 3.71×) over baseline systems, significantly reduces GPU memory consumption, and provides a plug-and-play API for seamless integration.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: Question Answering

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Complex Logical Query Answering (CLQA) involves intricate multi-hop logical reasoning over large-scale and potentially incomplete Knowledge Graphs (KGs). Although existing CLQA algorithms achieve high accuracy in answering such queries, their reasoning time and memory usage scale significantly with the number of First-Order Logic (FOL) operators involved, creating serious challenges for practical deployment. In addition, current research primarily focuses on algorithm-level optimizations for CLQA tasks, often overlooking compiler-level optimizations, which can offer greater generality and scalability. To address these limitations, we introduce a Knowledge Graph Compiler, namely KGCompiler, the first deep learning compiler specifically designed for CLQA tasks. By incorporating KG-specific optimizations proposed in this paper, KGCompiler enhances the reasoning performance of CLQA algorithms without requiring additional manual modifications to their implementations. At the same time, it significantly reduces memory usage. Extensive experiments demonstrate that KGCompiler accelerates CLQA algorithms by factors ranging from 1.04x to 8.26x, with an average speedup of 3.71x. We also provide an interface to enable hands-on experience with KGCompiler.

Problem

• Optimizes reasoning time and memory usage for CLQA.
• Introduces KGCompiler for deep learning compilation optimization.
• Enhances CLQA performance without manual algorithm modifications.

Innovation

• Deep learning compiler for Knowledge Graphs
• Optimizes CLQA without manual implementation changes
• Reduces memory usage and accelerates reasoning