发表机构
Accenture Labs（埃森哲实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对知识图谱链接预测中实体度不平衡导致的预测困难，提出推理时潜在搜索优化方法，在评估时融合已知与带外信息，显著提升不平衡三元组的预测性能。
AI 中文摘要
知识图谱嵌入模型已被广泛用于学习知识图谱中实体和关系的表示，以预测缺失的链接。然而，学习到的表示质量在图谱的不同区域之间差异很大。如果先前的研究将问题松散地与关系类型或度偏差联系起来，我们则表明问题更为普遍，并且与测试三元组中实体的度不平衡相关。特别是，当目标实体的度远小于锚定实体的度时，其预测极为困难。这在推荐系统及其他应用场景中至关重要，因为这些三元组代表了重要的边界情况。为解决此问题，我们提出了一种推理时潜在搜索优化方法，能够显著改善模型在最具不平衡性的三元组上的预测。该方法基于预训练模型，在评估时探索嵌入空间，融合已知信息和带外信息以缓解度不平衡偏差。我们在常见基准数据集的不平衡三元组上展示了我们方法的价值，其性能优于传统方法，为知识图谱嵌入模型在这些关键边界情况下的成功应用打开了大门。
英文摘要
Knowledge Graph Embedding models have been extensively used to learn representations of entities and relations in Knowledge Graphs for predicting missing links. However, the quality of the learned representations varies a lot across different areas of the graph. If previous research has loosely linked the problem to relation types or degree bias, we show that it is more widespread and it correlates with the degree imbalance of the entities in test triples. In particular, the prediction of a target entity that has a degree much smaller than the degree of the anchor entity is extremely problematic. This is critical in recommender systems and other use cases, where these triples represent important corner cases. To address this issue, we propose an inference-time latent search optimization method capable of significantly improving model predictions on the most imbalanced triples. Built on top of a pre-trained model, it explores the embedding space at evaluation time, blending known and out-of-band information to mitigate the degree imbalance bias. We show the value of our approach on imbalanced triples from common benchmark datasets, where we outperform conventional methods, opening the door to the successful adoption of Knowledge Graph Embedding models on these critical corner cases.
