MetaTKG：学习进化元知识用于时态知识图谱推理
MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning
摘要：
时态知识图谱推理（TKG）的目的是基于给定的历史来预测未来的事实。预测的关键挑战之一是了解事实的演变。现有的研究大多侧重于探索历史上的演化信息，为实体和关系获取有效的时间嵌入，但忽略了事实演化模式的变化，这使得它们很难适应未来具有不同演化模式的数据。此外，随着时间的推移，随着事实的演变，新的实体不断出现。由于现有的模型高度依赖于历史信息来学习实体的嵌入，因此它们在历史信息很少的实体上表现不佳。为了解决这些问题，我们提出了一个新的时间元学习框架TKG推理，MetaTKG的简洁。具体地说，我们的方法把TKG预测看作是许多时间元任务，并利用设计的时间元学习器从这些元任务中学习进化元知识。该方法的目的是引导骨干学习，以适应未来的数据，并处理与历史信息很少的实体学习的元知识。特别地，在时间元学习器中，我们设计了一个门控集成模块，自适应地建立元任务之间的时间相关性。在四个广泛使用的数据集和三个主干上的大量实验表明，我们的方法可以大大提高性能。
英文摘要：
Reasoning over Temporal Knowledge Graphs (TKGs) aims to predict future facts based on given history. One of the key challenges for prediction is to learn the evolution of facts. Most existing works focus on exploring evolutionary information in history to obtain effective temporal embeddings for entities and relations, but they ignore the variation in evolution patterns of facts, which makes them struggle to adapt to future data with different evolution patterns. Moreover, new entities continue to emerge along with the evolution of facts over time. Since existing models highly rely on historical information to learn embeddings for entities, they perform poorly on such entities with little historical information. To tackle these issues, we propose a novel Temporal Meta-learning framework for TKG reasoning, MetaTKG for brevity. Specifically, our method regards TKG prediction as many temporal meta-tasks, and utilizes the designed Temporal Meta-learner to learn evolutionary meta-knowledge from these meta-tasks. The proposed method aims to guide the backbones to learn to adapt quickly to future data and deal with entities with little historical information by the learned meta-knowledge. Specially, in temporal meta-learner, we design a Gating Integration module to adaptively establish temporal correlations between meta-tasks. Extensive experiments on four widely-used datasets and three backbones demonstrate that our method can greatly improve the performance.
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。
