Replication Data for NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning (AAAI'24)

Dataset

DOI

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.

Further information can be found in the README.md.

Identifier
DOI	https://doi.org/10.18419/darus-3978
Metadata Access	https://darus.uni-stuttgart.de/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.18419/darus-3978

Provenance
Creator	Xiong, Bo ; Nayyeri, Mojtaba ; Luo, Linhao (ORCID: 0000-0003-0027-942X); Wang, Zihao ; Pan, Shirui (ORCID: 0000-0003-0794-527X); Staab, Steffen
Publisher	DaRUS
Contributor	Xiong, Bo; Staab, Steffen
Publication Year	2024
Funding Reference	European Commission info:eu-repo/grantAgreement/EC/H2020/860801
Rights	info:eu-repo/semantics/openAccess
OpenAccess	true
Contact	Xiong, Bo (Universität Stuttgart); Staab, Steffen (Universität Stuttgart)

Representation
Resource Type	Dataset
Format	text/plain; application/octet-stream; text/x-python; text/x-c; application/x-sh; image/jpeg; text/markdown
Size	69; 40322315; 47583243; 100; 98; 102; 40885243; 42038883; 49248611; 50656403; 48696571; 42985875; 50682003; 48440571; 49235811; 47468043; 96; 97; 99; 83; 101; 55; 84; 85; 86; 2445; 2519; 2524; 23717; 218307; 207617; 7278; 4799; 2234; 2249; 2273; 1501; 78528; 5999; 6104; 5379; 5467; 5406; 5494; 7827; 9424; 9567; 7570; 13480; 9434; 7357; 13481; 7828; 7338; 10362; 10364; 7941; 2061; 2125; 2130; 4612; 2409; 2447; 2450; 339287; 999756; 280057; 4741631; 2303; 2008; 11; 5059; 5169; 10169; 10330; 9538; 9682; 9574; 9718; 9634; 7877; 7989; 7913; 8025; 9854; 7973; 7979; 7894; 8008; 8013; 8752; 8757; 4553; 4558; 6391; 6495; 6494; 359; 243; 345; 438; 773; 311; 365; 444; 393; 247; 317; 371; 351; 271; 458; 375; 389; 341; 840; 395; 250; 174; 203; 675; 327; 242; 108; 426; 297; 485; 495; 519; 113; 1500; 1512; 1536; 1046; 9817; 9831; 8347; 831; 849; 873; 318; 2175; 2155; 2173; 2482; 7589; 13787; 7608; 13791; 10986; 7612; 13789; 22; 10990; 279154; 11097; 4439; 4513; 4518; 894; 10871; 19183; 57384; 48049; 136; 12154; 54927; 15764; 63310; 1160; 161; 13610; 106; 33; 1789; 1817; 1822; 2855; 2899; 2904; 21429; 2694; 1440; 1460; 1484; 951; 2140; 2150; 954; 501; 511; 535; 121; 144; 1645; 390707; 437; 9011; 50384; 37501; 858; 50326; 49255; 6766; 2121; 39051; 298; 291; 38736; 84883; 8655; 986; 4414; 4475; 4499; 4286; 12564; 12044; 11113; 20065; 15767; 683050; 6036; 62468; 90417; 403126; 3116076; 99800; 173354; 14199; 312255; 15955; 6447; 6384; 6408; 5703; 5995; 6080; 6821; 7867; 3927; 3999; 4000; 3393; 2612; 2615; 3107; 3161; 3164; 3045; 3079; 3084; 706; 593; 11138; 7803; 50316; 12106; 390515; 1976; 22127; 85098; 39115; 1745
Version	1.0
Discipline	Other