.png){kind=icon}
.png){kind=icon}
Return
A lightweight knowledge reasoning method for large-scale knowledge graphs
.png){kind=icon}
PRE
AI
DOI：10.1007/s11227-026-08447-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Traditional Graph Attention Networks (GAT) exhibit inherent limitations when deployed for knowledge reasoning tasks, especially in processing vast graph data and the high-performance computing requirements (HPC). To address these challenges, we propose a lightweight GAT model for knowledge reasoning. First, to mitigate the constraints imposed by graph scale and enable efficient node representation learning, we introduce an inverse index query method to efficiently select triples from a large knowledge base to construct the target subgraph. Then, to further boost the computational efficiency of GAT, we design a lightweight method that integrates multi-level knowledge distillation and post-training parameter quantization, while ensuring model performance and reducing model parameters and memory usage. Experimental results show that our model has superior performance and demonstrates remarkable improvements in real-time computing efficiency compared to other benchmark models.
Keywords:
GAT
Inverted index
Knowledge distillation
Parameter quantization
Journal
T
IF:
0
Papers:
647
Citations:
0
View more organizations