Knowledge graph embedding model with attention-based high-low level features interaction convolutional network |
| |
| Institution: | 1. Department of Marketing, Business School, Nankai University, MBA Hall, Nankai University, 121 Baidi Road, Nankai District, Tianjin, China, 300071;2. Department of Information Resources Management, Business School, Nankai University, MBA Hall, Nankai University, 121 Baidi Road, Nankai District, Tianjin, China, 300071;3. School of Information, Kent State University, 314 University Library, 1125 Risman Drive, Kent, OH, United States, 44242-0001 |
| |
| Abstract: | Knowledge graphs are sizeable graph-structured knowledge with both abstract and concrete concepts in the form of entities and relations. Recently, convolutional neural networks have achieved outstanding results for more expressive representations of knowledge graphs. However, existing deep learning-based models exploit semantic information from single-level feature interaction, potentially limiting expressiveness. We propose a knowledge graph embedding model with an attention-based high-low level features interaction convolutional network called ConvHLE to alleviate this issue. This model effectively harvests richer semantic information and generates more expressive representations. Concretely, the multilayer convolutional neural network is utilized to fuse high-low level features. Then, features in fused feature maps interact with other informative neighbors through the criss-cross attention mechanism, which expands the receptive fields and boosts the quality of interactions. Finally, a plausibility score function is proposed for the evaluation of our model. The performance of ConvHLE is experimentally investigated on six benchmark datasets with individual characteristics. Extensive experimental results prove that ConvHLE learns more expressive and discriminative feature representations and has outperformed other state-of-the-art baselines over most metrics when addressing link prediction tasks. Comparing MRR and Hits@1 on FB15K-237, our model outperforms the baseline ConvE by 13.5% and 16.0%, respectively. |
| |
| Keywords: | Link prediction Knowledge graph embedding Convolutional neural network Criss-cross attention mechanism High-low level features interaction |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
