BoxE: A Box Embedding Model for Knowledge Base Completion
Authors: Ralph Abboud, Ismail Ceylan, Thomas Lukasiewicz, Tommaso Salvatori
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct a detailed experimental analysis, and show that Box E achieves state-of-the-art performance, both on benchmark knowledge graphs and on more general KBs, and we empirically show the power of integrating logical rules. |
| Researcher Affiliation | Academia | Ralph Abboud, Ismail Ilkan Ceylan, Thomas Lukasiewicz, Tommaso Salvatori Department of Computer Science University of Oxford, UK {firstame.lastname}@cs.ox.ac.uk |
| Pseudocode | No | The paper does not contain any sections explicitly labeled 'Pseudocode' or 'Algorithm', nor does it present any structured code blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology. |
| Open Datasets | Yes | In this experiment, we run Box E on the KGC benchmarks FB15k-237, WN18RR, and YAGO3-10... These datasets contain facts with arities up to 6 and 5, respectively... For example, KBs such as YAGO [24], NELL [26], Knowledge Vault [9], and Freebase [2] contain millions of facts... |
| Dataset Splits | Yes | We train Box E for up to 1000 epochs, with validation checkpoints every 100 epochs and the checkpoint with highest MRR used for testing. |
| Hardware Specification | No | The paper states: 'Experiments for this work were conducted on servers provided by the Advanced Research Computing (ARC) cluster administered by the University of Oxford.' This mentions a general computing environment but does not provide specific hardware details like GPU or CPU models. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., library names like PyTorch or TensorFlow with their respective versions) needed to replicate the experiment. |
| Experiment Setup | No | The paper mentions: 'Further details about experimental setup, as well as hyperparameter choices and dataset properties, can be found in the appendix.' However, these specific details are not provided in the main text of the paper. |