RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
Authors: Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, Jian Tang
ICLR 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on multiple benchmark knowledge graphs show that the proposed Rotat E model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction. |
| Researcher Affiliation | Collaboration | Zhiqing Sun 1 , Zhi-Hong Deng1, Jian-Yun Nie3, Jian Tang2,4,5 1Peking University, China 2Mila-Quebec Institute for Learning Algorithms, Canada 3Universit e de Montr eal, Canada 4HEC Montr eal, Canada 5CIFAR AI Research Chair {1500012783, zhdeng}@pku.edu.cn nie@iro.umontreal.ca jian.tang@hec.ca |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The codes of our paper are available online: https://github.com/Deep Graph Learning/ Knowledge Graph Embedding. |
| Open Datasets | Yes | We evaluate the Rotat E on four large knowledge graph benchmark datasets including FB15k (Bordes et al., 2013), WN18 (Bordes et al., 2013), FB15k-237 (Toutanova & Chen, 2015) and WN18RR (Dettmers et al., 2017). |
| Dataset Splits | Yes | Dataset #entity #relation #training #validation #test FB15k 14,951 1,345 483,142 50,000 59,071 WN18 40,943 18 141,442 5,000 5,000 FB15k-237 14,541 237 272,115 17,535 20,466 WN18RR 40,943 11 86,835 3,034 3,134 |
| Hardware Specification | No | The paper does not explicitly state the hardware specifications (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not specify the version numbers for any software dependencies (e.g., libraries, frameworks, or programming languages) used in the experiments. |
| Experiment Setup | Yes | Hyperparameter Settings. We use Adam (Kingma & Ba, 2014) as the optimizer and fine-tune the hyperparameters on the validation dataset. The ranges of the hyperparameters for the grid search are set as follows: embedding dimension5 k {125, 250, 500, 1000}, batch size b {512, 1024, 2048}, self-adversarial sampling temperature α {0.5, 1.0}, and fixed margin γ {3, 6, 9, 12, 18, 24, 30}. Both the real and imaginary parts of the entity embeddings are uniformly initialized, and the phases of the relation embeddings are uniformly initialized between 0 and 2π. |