Knowledge graph embedding (KGE) that maps entities and relations into vector representations is essential for downstream tasks. Conventional KGE methods require relatively high-dimensional entity representations to preserve the structural information of knowledge graph, but lead to oversized model parameters. Recent methods reduce model parameters by adopting low-dimensional entity representations, while developing techniques (e.g., knowledge distillation) to compensate for the reduced dimension. However, such operations produce degraded model accuracy and limited reduction of model parameters. Specifically, we view the concatenation of all entity representations as an embedding layer, and then conventional KGE methods that adopt high-dimensional entity representations equal to enlarging the width of the embedding layer to gain expressiveness. To achieve parameter efficiency without sacrificing accuracy, we instead increase the depth and propose a deeper embedding network for entity representations, i.e., a narrow embedding layer and a multi-layer dimension lifting network (LiftNet). Experiments on three public datasets show that the proposed method (implemented based on TransE and DistMult) with 4-dimensional entity representations achieves more accurate link prediction results than counterpart parameter-efficient KGE methods and strong KGE baselines, including TransE and DistMult with 512-dimensional entity representations.

翻译：知识图谱嵌入（KGE）将实体和关系映射为向量表示，是下游任务的基础。传统KGE方法需要较高维度的实体表示来保留知识图谱的结构信息，但会导致模型参数过大。近期方法采用低维实体表示以减少模型参数，同时发展知识蒸馏等技术来补偿维度降低带来的损失。然而，这类操作会降低模型精度，且模型参数的缩减程度有限。具体而言，我们将所有实体表示的拼接视为一个嵌入层，传统KGE方法采用高维实体表示等同于扩展嵌入层的宽度以增强表达能力。为在不牺牲精度的情况下实现参数效率，我们转而增加深度，并提出一种用于实体表示的更深层次嵌入网络，即窄嵌入层与多层维度提升网络（LiftNet）。在三个公开数据集上的实验表明，所提方法（基于TransE和DistMult实现）在4维实体表示下取得了比同等参数高效KGE方法及强基线的KGE方法（包括采用512维实体表示的TransE和DistMult）更准确的链接预测结果。