Multi-Relational Graph Representation Learning with Bayesian Gaussian Process Network
Authors: Guanzheng Chen, Jinyuan Fang, Zaiqiao Meng, Qiang Zhang, Shangsong Liang5530-5538
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our GGPN in link prediction and entity classification tasks, and the experimental results demonstrate the superiority of our method. Our code is available at https://github.com/sysu-gzchen/GGPN. |
| Researcher Affiliation | Academia | 1 School of Computer Science and Engineering, Sun Yat-sen University, China 2 Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China 3 School of Computing Science, University of Glasgow, United Kingdom 4 Hangzhou Innovation Center, Zhejiang University, China 5 College of Computer Science and Technology, Zhejiang University, China 6 Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates |
| Pseudocode | No | The paper describes the model architecture and mathematical formulations but does not include any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/sysu-gzchen/GGPN. |
| Open Datasets | Yes | We adopt two widely used benchmark datasets in our link prediction experiments: FB15K-237 (Toutanova et al. 2015) and WN18RR (Dettmers et al. 2018)... We conduct experiments on four RDF-format datasets (Ristoski, De Vries, and Paulheim 2016): AIFB, MUTAG, BGS, and AM. |
| Dataset Splits | Yes | We randomly divide 20% of training data as the validation dataset for hyperparameters tuning. We also use grid search to find the hyperparameters based on their performance on validation sets. |
| Hardware Specification | No | The paper mentions running experiments but does not provide specific hardware details (e.g., GPU models, CPU types, memory). |
| Software Dependencies | No | The paper states that Adam was used as the optimizer, but it does not specify software dependencies with version numbers (e.g., Python version, PyTorch/TensorFlow version, specific library versions). |
| Experiment Setup | Yes | The input features of entities and relations to our GGPN are randomly initialized with a size of 100, and the output embedding size of both entities and relations are set to 200. We use Adam (Kingma and Ba 2015) as the optimizer and perform grid search to select the hyperparameters that have the best performance on validation sets. |