发表机构
University of Southern California; Islamic University of Technology（南加州大学; 伊斯兰技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出QUEST方法，通过谱初始化和狄利克雷能量正则化，提升不确定知识图谱补全的准确性、训练稳定性与检查点可靠性。
AI 中文摘要
不确定知识图谱（UKGs）通过为每个三元组分配连续置信度分数扩展了知识图谱。由于大部分可能的三元组缺乏观测到的置信度，现有方法依赖半监督学习生成伪标签，这些方法在初始化实体嵌入时未使用置信度加权图，丢弃了其全局社区和枢纽结构。我们提出了QUEST，该方法未在标准置信度分布学习流程中添加可训练参数：首先，QUEST利用置信度加权图拉普拉斯的最小非平凡特征向量初始化实体嵌入，在训练前融入社区和枢纽结构；其次，QUEST应用无偏小批量狄利克雷能量正则化项，以强制早期结构一致性。在两个UKG数据集上，QUEST在8个指标-数据集对中的6个上提升了置信度预测和链接预测性能，优于现有方法，在剩余2个上与之前最佳表现相当，同时消除了在稠密图上观测到的不稳定峰值。这些结果表明，谱结构先验结合图狄利克雷能量正则化项可提升UKG补全的准确性、训练稳定性和检查点可靠性。
英文摘要
Uncertain knowledge graphs (UKGs) extend knowledge graphs by assigning each triple a continuous confidence score. Since most possible triples lack observed confidences, recent methods rely on semi-supervised learning to generate pseudo-labels. These methods initialize entity embeddings without using the confidence-weighted graph, discarding its global community and hub structure. We introduce QUEST, which adds no trainable parameters to the standard confidence-distribution learning pipeline. First, QUEST initializes entity embeddings using the smallest non-trivial eigenvectors of the confidence-weighted graph Laplacian, incorporating community and hub structure before training. Second, QUEST applies an unbiased mini-batch Dirichlet energy regularizer to enforce early-stage structural consistency. On two UKG datasets, QUEST improves confidence prediction and link prediction on six of eight metric-dataset pairs over prior methods and matches the previous best on the remaining two, while removing the instability spike observed on dense graphs. These results indicate that spectral structural priors combined with a graph Dirichlet energy regularizer improve accuracy, training stability, and checkpoint reliability in UKG completion.
