KGCompiler: Deep Learning Compilation Optimization for Knowledge Graph Complex Logical Query Answering
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 17 of its 24 references that are in the map. First posted on arXiv 4 Mar 2025.
Builds on
17 of 24 references.
Closest ancestors · 1
Same direction, newest first
Other references · 16
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 266
- 2020Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddingscited by 171
- 2018DKN: Deep Knowledge-Aware Network for News Recommendationcited by 137
- 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 129
- 2018Embedding Logical Queries on Knowledge Graphscited by 120
- 2020Complex Query Answering with Neural Link Predictorscited by 99
- 2021ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphscited by 78
- 2019Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answeringcited by 68
- 2022Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimizationcited by 29
- 2022Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programscited by 28
- 2021Logic Embeddings for Complex Query Answeringcited by 17
4 more
- 2021SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphscited by 17
- 2023Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictorscited by 13
- 2023Wafer-scale Computing: Advancements, Challenges, and Future Perspectivescited by 6
- 2023Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphscited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases
- 2023Complex Logical Reasoning over Knowledge Graphs using Large Language Models
- 2023EFOk-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation
- 2024A Foundation Model for Zero-shot Logical Query Reasoning
- 2023Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs
- 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
- 2024Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
- 2026KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering