Multi-view Knowledge Graph Embedding for Entity Alignment

Authors: Qingheng Zhang, Zequn Sun, Wei Hu, Muhao Chen, Lingbing Guo, Yuzhong Qu

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments on real-world datasets show that the proposed framework significantly outperforms the state-of-the-art embeddingbased entity alignment methods.
Researcher Affiliation Academia 1 State Key Laboratory for Novel Software Technology, Nanjing University, China 2 Department of Computer Science, University of California, Los Angeles, USA
Pseudocode Yes Algorithm 1: Combined training process of Multi KE
Open Source Code Yes The source code is accessible online.2 2https://github.com/nju-websoft/Multi KE
Open Datasets Yes In our experiments, we reused two datasets, namely DBP-WD and DBP-YG, recently proposed in [Sun et al., 2018].
Dataset Splits No The paper states '30% reference entity alignment as seed and leaves the remaining for evaluating entity alignment performance' but does not specify a distinct validation set.
Hardware Specification No The paper does not provide any specific details about the hardware used for the experiments.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used for the experiments.
Experiment Setup Yes The following hyper-parameters were used in the experiments. Each training took Q = 200 epochs with learning rate 0.001. For the relation view embedding, 10 negative facts were sampled for each real relation fact. For the attribute view embedding, the number of filters was 2 and the convolution kernel size was 2 4 (i.e., c = 4). The activation function for the autoencoder and CNN was tanh( ). For the relation and attribute identity inference, we set α1 = 0.6, α2 = 0.4 and η = 0.9. The embedding dimension d was set to 75 for all the comparative methods.