ConvD: Attention Enhanced Dynamic Convolutional Embeddings for Knowledge Graph Completion
This addresses knowledge graph completion for AI applications, representing a strong incremental improvement over existing convolutional embedding models.
The paper tackles knowledge graph incompleteness by proposing ConvD, a dynamic convolutional embedding model that reshapes relation embeddings into internal convolution kernels and uses an attention mechanism to weight them. Experiments show average improvements of 3.28% to 14.69% across metrics while reducing parameters by 50.66% to 85.40% compared to state-of-the-art methods.
Knowledge graphs often suffer from incompleteness issues, which can be alleviated through information completion. However, current state-of-the-art deep knowledge convolutional embedding models rely on external convolution kernels and conventional convolution processes, which limits the feature interaction capability of the model. This paper introduces a novel dynamic convolutional embedding model, ConvD, which directly reshapes relation embeddings into multiple internal convolution kernels. This approach effectively enhances the feature interactions between relation embeddings and entity embeddings. Simultaneously, we incorporate a priori knowledge-optimized attention mechanism that assigns different contribution weight coefficients to the multiple relation convolution kernels in dynamic convolution, further boosting the expressive power of the model. Extensive experiments on various datasets show that our proposed model consistently outperforms the state-of-the-art baseline methods, with average improvements ranging from 3.28% to 14.69% across all model evaluation metrics, while the number of parameters is reduced by 50.66% to 85.40% compared to other state-of-the-art models.