Knowledge graph completion (KGC) aims to predict unseen edges in knowledge graphs (KGs), resulting in the discovery of new facts. A new class of methods have been proposed to tackle this problem by aggregating path information. These methods have shown tremendous ability in the task of KGC. However they are plagued by efficiency issues. Though there are a few recent attempts to address this through learnable path pruning, they often sacrifice the performance to gain efficiency. In this work, we identify two intrinsic limitations of these methods that affect the efficiency and representation quality. To address the limitations, we introduce a new method, TAGNet, which is able to efficiently propagate information. This is achieved by only aggregating paths in a fixed window for each source-target pair. We demonstrate that the complexity of TAGNet is independent of the number of layers. Extensive experiments demonstrate that TAGNet can cut down on the number of propagated messages by as much as 90% while achieving competitive performance on multiple KG datasets. The code is available at https://github.com/HarryShomer/TAGNet.

翻译：知识图谱补全（KGC）旨在预测知识图谱（KG）中未出现的边，从而发现新事实。近期一类新方法通过聚合路径信息来解决该问题，这些方法在KGC任务中展现出卓越能力，但受困于效率瓶颈。尽管已有少数工作尝试通过可学习的路径剪枝来提升效率，但这些方法往往以牺牲性能为代价。本文识别出该类方法在影响效率与表征质量方面的两个本质局限。针对这些局限，我们提出新方法TAGNet，它能高效传播信息——其核心思想是通过仅对每对源-目标实体在固定窗口内的路径进行聚合。我们证明TAGNet的复杂度与层数无关。大量实验表明，TAGNet可将传播消息数量削减高达90%，同时在多个知识图谱数据集上保持竞争性性能。代码已开源至https://github.com/HarryShomer/TAGNet。