2022/05/05 by Yongqi Zhang, Zhang, Yongqi, Zhanke Zhou +5 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2205.02460
openalex publication_date 2022/05/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
While hyper-parameters (HPs) are important for knowledge graph (KG) learning, existing methods fail to search them efficiently. To solve this problem, we first analyze the properties of different HPs and measure the transfer ability from small subgraph to the full graph. Based on the analysis, we propose an efficient two-stage search algorithm KGTuner, which efficiently explores HP configurations on small subgraph at the first stage and transfers the top-performed configurations for fine-tuning on the large full graph at the second stage. Experiments show that our method can consistently find better HPs than the baseline algorithms within the same time budget, which achieves 9.1% average relative improvement for four embedding models on the large-scale KGs in open graph benchmark.