NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning

Authors: Bo Xiong, Mojtaba Nayyeri, Linhao Luo, Zihao Wang, Shirui Pan, Steffen Staab

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experimental results showcase Nest E s significant performance gains over current baselines in triple prediction and conditional link prediction.
Researcher Affiliation Academia 1University of Stuttgart, Stuttgart, Germany 2Monash University, Melbourne, Australia 3Griffith University, Queensland, Australia 4University of Southampton, Southampton, United Kingdom
Pseudocode No The paper describes mathematical operations and model components but does not provide pseudocode or a clearly labeled algorithm block.
Open Source Code Yes The code and pre-trained models are open available at https://github.com/xiongbo010/Nest E.
Open Datasets Yes We utilize three benchmark KGs: FBH, FBHE, and DBHE, that contain nested facts and are constructed by (Chung and Whang 2023).
Dataset Splits Yes We split T and b T into training, validation, and test sets in an 8:1:1 ratio.
Hardware Specification No The paper does not provide any specific details about the hardware used for running experiments.
Software Dependencies No The paper states 'We implement the framework based on Open KE 4 and the code 5' but does not specify version numbers for Open KE or any other software dependencies.
Experiment Setup Yes The detailed hyperparameter settings can be found in the Appendix.