Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Quaternion Knowledge Graph Embeddings
Authors: SHUAI ZHANG, Yi Tay, Lina Yao, Qi Liu
NeurIPS 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrate that our method achieves state-of-the-art performance on four wellestablished knowledge graph completion benchmarks. |
| Researcher Affiliation | Academia | University of New South Wales ψNanyang Technological University, φUniversity of Oxford |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | Datasets Description: We conducted experiments on four widely used benchmarks, WN18, FB15K, WN18RR and FB15K-237, of which the statistics are summarized in Table 2. |
| Dataset Splits | Yes | The best models are selected by early stopping on the validation set. Table 2 also includes a '#validation' column with specific counts for each dataset. |
| Hardware Specification | No | The paper only vaguely mentions 'tested it on a single GPU' without providing any specific model numbers or hardware details. |
| Software Dependencies | No | The paper states 'We implemented our model using pytorch4', but 'pytorch4' refers to footnote 4 (https://pytorch.org/) and does not specify a version number. |
| Experiment Setup | Yes | The embedding size k is tuned amongst {50, 100, 200, 250, 300}. Regularization rate λ1 and λ2 are searched in {0, 0.01, 0.05, 0.1, 0.2}. Learning rate is fixed to 0.1 without further tuning. The number of negatives (#neg) per training sample is selected from {1, 5, 10, 20}. We create 10 batches for all the datasets. |