用深度学习编译器优化知识图谱复杂查询，提速超3倍且省内存。
KGCompiler: Deep Learning Compilation Optimization for Knowledge Graph Complex Logical Query Answering
- 基于深度学习的编译器架构，针对知识图谱查询自动优化逻辑运算。
- 实测加速比1.04倍到8.26倍，平均提升3.71倍，内存占用显著降低。
- 无需修改原有算法代码，适合知识图谱推理系统开发者快速部署。
复杂逻辑查询回答（CLQA）涉及在大规模且可能不完整的知识图谱上进行复杂的多跳逻辑推理。尽管现有CLQA算法在回答这类查询时具有高准确率，但其推理时间和内存消耗随一阶逻辑（FOL）操作符数量显著增加，严重制约实际部署。此外，当前研究主要聚焦于算法级优化，常忽视可带来更高通用性与可扩展性的编译器级优化。为此，本文提出首个专为CLQA任务设计的深度学习编译器——KGCompiler。通过引入本文提出的知识图谱特异性优化策略，KGCompiler在不需额外手动修改算法实现的前提下，显著提升CLQA算法的推理性能，并大幅降低内存使用。大量实验表明，KGCompiler使CLQA算法加速比达1.04倍至8.26倍，平均加速3.71倍。同时，我们提供了交互接口，支持用户动手体验。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。