Completing missing facts is a fundamental task for temporal knowledge graphs (TKGs). Recently, graph neural network (GNN) based methods, which can simultaneously explore topological and temporal information, have become the state-of-the-art (SOTA) to complete TKGs. However, these studies are based on hand-designed architectures and fail to explore the diverse topological and temporal properties of TKG. To address this issue, we propose to use neural architecture search (NAS) to design data-specific message passing architecture for TKG completion. In particular, we develop a generalized framework to explore topological and temporal information in TKGs. Based on this framework, we design an expressive search space to fully capture various properties of different TKGs. Meanwhile, we adopt a search algorithm, which trains a supernet structure by sampling single path for efficient search with less cost. We further conduct extensive experiments on three benchmark datasets. The results show that the searched architectures by our method achieve the SOTA performances. Besides, the searched models can also implicitly reveal diverse properties in different TKGs. Our code is released in https://github.com/striderdu/SPA.
翻译:弥补缺失的事实是时间知识图(TKGs)的一项基本任务。最近,基于图形神经网络(GNN)的方法,可以同时探索表层和时间信息,已成为完成TKG的先进技术(SOTA),然而,这些研究以手工设计的建筑为基础,未能探索TKG的各种地形和时间特性。为了解决这一问题,我们提议使用神经结构搜索(NAS)来设计数据特定信息传递结构,以完成TKG。特别是,我们开发了一个探索TKGs的表层和时间信息的普遍框架。基于这个框架,我们设计了一个表达式搜索空间,以充分捕捉不同TKGs的各种特性。同时,我们采用了一种搜索算法,通过抽样单一路径来培训超级网络结构,以便以较低成本高效搜索。我们进一步对三个基准数据集进行了广泛的实验。结果显示,我们方法搜索的架构实现了SOTA的性能。此外,搜索模型还可以隐含地揭示不同TKGs的不同属性。我们的代码公布在 https://githumber/comub.com.