通过半监督置信度分布学习实现不确定知识图谱补全
Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning
AI总结：
针对不确定知识图谱中三元组置信度分布极度不平衡的问题，提出半监督 ssCDL 方法，通过置信度分布转换与元学习伪标签迭代增强嵌入学习，并在两个数据集上优于现有基线。
摘要：
不确定知识图谱（UKG）为每个三元组关联一个置信度分数，以提供更精确的知识表示。近年来，由于真实世界的 UKG 存在不完整性，不确定知识图谱（UKG）补全吸引了更多关注，其目标是补全缺失的三元组及其置信度。当前研究尝试学习 UKG 嵌入来解决这一问题，但它们忽略了三元组置信度极度不平衡的分布。这导致所学嵌入不足以实现高质量的 UKG 补全。因此，为解决上述问题，本文提出一种用于 UKG 补全的新型半监督置信度分布学习（ssCDL）方法，其中每个三元组置信度被转换为一个置信度分布，以引入不同置信度的更多监督信息，从而强化嵌入学习过程。ssCDL 通过在有标签数据（即带有置信度的现有三元组）和具有伪标签的无标签数据（即带有生成置信度的未见三元组）上进行关系学习，迭代地学习 UKG 嵌入；这些伪标签由元学习预测，用于扩充训练数据并重新平衡三元组置信度的分布。在两个 UKG 数据集上的实验表明，ssCDL 在不同评估指标上始终优于最先进的基线方法。
英文摘要：
Uncertain knowledge graphs (UKGs) associate each triple with a confidence score to provide more precise knowledge representations. Recently, since real-world UKGs suffer from the incompleteness, uncertain knowledge graph (UKG) completion attracts more attention, aiming to complete missing triples and confidences. Current studies attempt to learn UKG embeddings to solve this problem, but they neglect the extremely imbalanced distributions of triple confidences. This causes that the learnt embeddings are insufficient to high-quality UKG completion. Thus, in this paper, to address the above issue, we propose a new semi-supervised Confidence Distribution Learning (ssCDL) method for UKG completion, where each triple confidence is transformed into a confidence distribution to introduce more supervision information of different confidences to reinforce the embedding learning process. ssCDL iteratively learns UKG embedding by relational learning on labeled data (i.e., existing triples with confidences) and unlabeled data with pseudo labels (i.e., unseen triples with the generated confidences), which are predicted by meta-learning to augment the training data and rebalance the distribution of triple confidences. Experiments on two UKG datasets demonstrate that ssCDL consistently outperforms state-of-the-art baselines in different evaluation metrics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
