用图谱谱结构初始化嵌入，提升不确定知识图谱补全的精度与稳定性。
Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion
- 基于置信度加权图拉普拉斯矩阵最小非平凡特征向量初始化实体嵌入，保留全局社区与枢纽结构。
- 引入无偏小批量狄利克雷能量正则项，早期强化图结构一致性，避免密集图训练波动。
- 在两个数据集上6/8指标超越前人方法，且消除稠密图下的训练不稳问题，适合高置信度需求场景。
不确定知识图谱（UKG）通过为每条三元组分配连续置信度得分扩展了传统知识图谱。由于多数可能的三元组缺乏观测置信度，现有方法依赖半监督学习生成伪标签。这些方法在训练前未使用置信度加权图进行实体嵌入初始化，忽略了其全局社区与枢纽结构。本文提出QUEST，不增加标准置信度分布学习流水线中的可训练参数。首先，利用置信度加权图拉普拉斯矩阵的最小非平凡特征向量初始化实体嵌入，提前融合图结构信息。其次，引入无偏小批量狄利克雷能量正则项，强制训练初期保持结构一致性。在两个UKG数据集上，QUEST在八个指标-数据集组合中的六个上优于先前方法，并在其余两个上达到最佳水平，同时消除了密集图上的训练不稳定现象。结果表明，结合谱结构先验与图狄利克雷能量正则项能提升准确率、训练稳定性和检查点可靠性。
原文摘要 · Abstract (English)
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.
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。