Convolutional Complex Knowledge Graph Embeddings
This work addresses link prediction in knowledge graphs, offering a more efficient and effective solution for applications in AI and data mining, though it is incremental in improving existing embedding techniques.
The paper tackles the problem of predicting missing links in knowledge graphs by introducing ConEx, a method using 2D convolution and Hermitian inner products of complex embeddings, which achieves superior performance on benchmark datasets like WN18RR and FB15K-237 while reducing parameters by at least 8 times compared to state-of-the-art models.
In this paper, we study the problem of learning continuous vector representations of knowledge graphs for predicting missing links. We present a new approach called ConEx, which infers missing links by leveraging the composition of a 2D convolution with a Hermitian inner product of complex-valued embedding vectors. We evaluate ConEx against state-of-the-art approaches on the WN18RR, FB15K-237, KINSHIP and UMLS benchmark datasets. Our experimental results show that ConEx achieves a performance superior to that of state-of-the-art approaches such as RotatE, QuatE and TuckER on the link prediction task on all datasets while requiring at least 8 times fewer parameters. We ensure the reproducibility of our results by providing an open-source implementation which includes the training, evaluation scripts along with pre-trained models at https://github.com/conex-kge/ConEx.