Many Graph Neural Networks (GNNs) are proposed for Knowledge Graph Embedding (KGE). However, lots of these methods neglect the importance of the information of relations and combine it with the information of entities inefficiently, leading to low expressiveness. To address this issue, we introduce a general knowledge graph encoder incorporating tensor decomposition in the aggregation function of Relational Graph Convolutional Network (R-GCN). In our model, neighbor entities are transformed using projection matrices of a low-rank tensor which are defined by relation types to benefit from multi-task learning and produce expressive relation-aware representations. Besides, we propose a low-rank estimation of the core tensor using CP decomposition to compress and regularize our model. We use a training method inspired by contrastive learning, which relieves the training limitation of the 1-N method on huge graphs. We achieve favorably competitive results on FB15k-237 and WN18RR with embeddings in comparably lower dimensions.

翻译：许多图神经网络已被提出用于知识图谱嵌入。然而，这些方法中的大多数忽视了关系信息的重要性，并且未能高效地将其与实体信息结合，导致表达能力不足。为解决这一问题，我们引入了一种通用知识图谱编码器，在关系图卷积网络的聚合函数中融入张量分解。在我们的模型中，邻居实体通过由关系类型定义的低秩张量投影矩阵进行变换，从而受益于多任务学习并生成具有表达力的关系感知表示。此外，我们提出利用CP分解对核心张量进行低秩估计，以压缩和正则化模型。我们采用一种受对比学习启发的训练方法，缓解了1-N方法在大型图上的训练限制。在FB15k-237和WN18RR数据集上，我们利用相对较低维度的嵌入取得了具有竞争力的优异结果。