ConvMS: Improving Convolutional Knowledge Graph Embeddings via Integrating Information of Multiple Subspaces

Abstract

Knowledge graphs are involved in more and more applications to further improve intelligence. Owing to the inherent incompleteness of knowledge graphs resulted from data updating and missing, a number of knowledge graph completion models are proposed in succession. To obtain better performance, many methods are of high complexity, making it time-consuming for training and inference. This paper proposes a simple but effective model using only shallow neural networks, which combines enhanced feature interaction and multi-subspace information integration. In the enhanced feature interaction module, entity and relation embeddings are almost peer-to-peer interacted via multi-channel 2D convolution. In the multi-subspace information integration module, entity and relation embeddings are projected to multiple subspaces to extract multi-view information to further boost performance. Extensive experiments on widely used datasets show that the proposed model outperforms a series of strong baselines. And ablation studies demonstrate the effectiveness of each submodule in the model.