This code is a PyTorch implementation of the paper "NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning (AAAI'24)".NestE is a knowledge graph embedding method that can encode nested facts represented by quoted triples (h,r,t) in which the subject and object are triples themselves, e.g., ((BarackObama, holds_position, President), succeed_by, (DonaldTrump, holds_position, President)).We implement six variant models of NetsE based on different hypercomplex number systems. NestE_Q.py for NestE with quaternion. NestE_H.py for NestE with hyperbolic quaternion. NestE_D.py for NestE with split quaternion. NestE_B.py, NestE_HB.py, and NestE_DB.py are the respective version with a translation component. This code is used to reproduce the experiments of the paper. To execute the code, follow the instructions in the README.md file.
%0 Generic
%1 https://doi.org/10.18419/darus-3978
%A Xiong, Bo
%A Nayyeri, Mojtaba
%A Luo, Linhao
%A Wang, Zihao
%A Pan, Shirui
%A Staab, Steffen
%D 2024
%I DaRUS
%K ki
%R 10.18419/DARUS-3978
%T Replication Data for NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning (AAAI'24)
%U https://darus.uni-stuttgart.de/citation?persistentId=doi:10.18419/darus-3978
%X This code is a PyTorch implementation of the paper "NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning (AAAI'24)".NestE is a knowledge graph embedding method that can encode nested facts represented by quoted triples (h,r,t) in which the subject and object are triples themselves, e.g., ((BarackObama, holds_position, President), succeed_by, (DonaldTrump, holds_position, President)).We implement six variant models of NetsE based on different hypercomplex number systems. NestE_Q.py for NestE with quaternion. NestE_H.py for NestE with hyperbolic quaternion. NestE_D.py for NestE with split quaternion. NestE_B.py, NestE_HB.py, and NestE_DB.py are the respective version with a translation component. This code is used to reproduce the experiments of the paper. To execute the code, follow the instructions in the README.md file.
@dataset{https://doi.org/10.18419/darus-3978,
abstract = {This code is a PyTorch implementation of the paper "NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning (AAAI'24)".NestE is a knowledge graph embedding method that can encode nested facts represented by quoted triples (h,r,t) in which the subject and object are triples themselves, e.g., ((BarackObama, holds_position, President), succeed_by, (DonaldTrump, holds_position, President)).We implement six variant models of NetsE based on different hypercomplex number systems. NestE_Q.py for NestE with quaternion. NestE_H.py for NestE with hyperbolic quaternion. NestE_D.py for NestE with split quaternion. NestE_B.py, NestE_HB.py, and NestE_DB.py are the respective version with a translation component. This code is used to reproduce the experiments of the paper. To execute the code, follow the instructions in the README.md file.},
added-at = {2024-11-10T12:05:30.000+0100},
author = {Xiong, Bo and Nayyeri, Mojtaba and Luo, Linhao and Wang, Zihao and Pan, Shirui and Staab, Steffen},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2b77698a4821997749899e12b775730aa/joy},
doi = {10.18419/DARUS-3978},
interhash = {b8b776e29ad9e2b21959c36cdc4fdbdb},
intrahash = {b77698a4821997749899e12b775730aa},
keywords = {ki},
publisher = {DaRUS},
timestamp = {2024-11-10T12:05:30.000+0100},
title = {Replication Data for NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning (AAAI'24)},
url = {https://darus.uni-stuttgart.de/citation?persistentId=doi:10.18419/darus-3978},
year = 2024
}
