Papers › RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

26 Feb 2019ICLR 2019 5arXiv:1902.10197archive 2025-07-28

Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, Jian Tang

We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links. The success of such a task heavily relies on the ability of modeling and inferring the patterns of (or between) the relations. In this paper, we present a new approach for knowledge graph embedding called RotatE, which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition. Specifically, the RotatE model defines each relation as a rotation from the source entity to the target entity in the complex vector space. In addition, we propose a novel self-adversarial negative sampling technique for efficiently and effectively training the RotatE model. Experimental results on multiple benchmark knowledge graphs show that the proposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1902.10197")

Code

Syntology Ran 0 of 5 code samples harvested from 1 repository linked to this paper; 5 have no recorded run.

By repository: community (archive-listed): 5 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

DeepGraphLearning/KnowledgeGraphEmbedding officialmentioned in paperpytorchMIT report
awslabs/dgl-ke mentioned on GitHubpytorchApache-2.0 report
davendw49/gakg mentioned on GitHubpytorchApache-2.0 report
snap-stanford/ConE mentioned on GitHubpytorch report
cui0523/Code6 mindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested; 0 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5unverified

Licence: 0 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from davendw49/gakg. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

data_loader davendw49/gakg/code/baselines/transH/TransH.py community (archive-listed) unverified Apache-2.0 (permissive) · f103f76a05c11c85 · report
dataloader davendw49/gakg/code/baselines/transE/TransE_pytoch.py community (archive-listed) unverified Apache-2.0 (permissive) · 0577997988d41269 · report
dataloader davendw49/gakg/code/baselines/transE/transE.py community (archive-listed) unverified Apache-2.0 (permissive) · dbe17b25039229ed · report
norm_l1 davendw49/gakg/code/baselines/transE/TransE_pytoch.py community (archive-listed) unverified Apache-2.0 (permissive) · 334b60ecd2bd5b68 · report
norm_l2 davendw49/gakg/code/baselines/transE/TransE_pytoch.py community (archive-listed) unverified Apache-2.0 (permissive) · 85ce51631a65b76e · report

Tasks

Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink Prediction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB122 RotatE HITS@3 70.8 #2 of 5 Archive leaderboard report
Link Prediction FB122 RotatE Hits@10 77.0 #2 of 5 Archive leaderboard report
Link Prediction FB122 RotatE Hits@5 73.57 #2 of 5 Archive leaderboard report
Link Prediction FB122 RotatE MRR 67.8 #2 of 5 Archive leaderboard report
Link Prediction FB15k pRotatE Hits@1 0.750 #6 of 23 Archive leaderboard report
Link Prediction FB15k pRotatE Hits@10 0.884 #6 of 23 Archive leaderboard report
Link Prediction FB15k pRotatE Hits@3 0.829 #6 of 23 Archive leaderboard report
Link Prediction FB15k pRotatE MR 43 #6 of 23 Archive leaderboard report
Link Prediction FB15k pRotatE MRR 0.799 #6 of 23 Archive leaderboard report
Link Prediction FB15k RotatE Hits@1 0.746 #7 of 23 Archive leaderboard report
Link Prediction FB15k RotatE Hits@10 0.884 #7 of 23 Archive leaderboard report
Link Prediction FB15k RotatE Hits@3 0.830 #7 of 23 Archive leaderboard report
Link Prediction FB15k RotatE MR 40 #7 of 23 Archive leaderboard report
Link Prediction FB15k RotatE MRR 0.797 #7 of 23 Archive leaderboard report
Link Prediction FB15k-237 RotatE Hits@1 0.241 #43 of 75 Archive leaderboard report
Link Prediction FB15k-237 RotatE Hits@10 0.533 #43 of 75 Archive leaderboard report
Link Prediction FB15k-237 RotatE Hits@3 0.375 #43 of 75 Archive leaderboard report
Link Prediction FB15k-237 RotatE MR 177 #43 of 75 Archive leaderboard report
Link Prediction FB15k-237 RotatE MRR 0.338 #43 of 75 Archive leaderboard report
Link Prediction FB15k-237 pRotatE Hits@1 0.23 #46 of 75 Archive leaderboard report
Link Prediction FB15k-237 pRotatE Hits@10 0.524 #46 of 75 Archive leaderboard report
Link Prediction FB15k-237 pRotatE Hits@3 0.365 #46 of 75 Archive leaderboard report
Link Prediction FB15k-237 pRotatE MR 178 #46 of 75 Archive leaderboard report
Link Prediction FB15k-237 pRotatE MRR 0.328 #46 of 75 Archive leaderboard report
Link Prediction WN18 RotatE Hits@1 0.944 #9 of 37 Archive leaderboard report
Link Prediction WN18 RotatE Hits@10 0.959 #9 of 37 Archive leaderboard report
Link Prediction WN18 RotatE Hits@3 0.952 #9 of 37 Archive leaderboard report
Link Prediction WN18 RotatE MR 309 #9 of 37 Archive leaderboard report
Link Prediction WN18 RotatE MRR 0.949 #9 of 37 Archive leaderboard report
Link Prediction WN18 pRotatE Hits@1 0.942 #14 of 37 Archive leaderboard report
Link Prediction WN18 pRotatE Hits@10 0.957 #14 of 37 Archive leaderboard report
Link Prediction WN18 pRotatE Hits@3 0.950 #14 of 37 Archive leaderboard report
Link Prediction WN18 pRotatE MR 254 #14 of 37 Archive leaderboard report
Link Prediction WN18 pRotatE MRR 0.947 #14 of 37 Archive leaderboard report
Link Prediction WN18RR RotatE Hits@1 0.428 #36 of 75 Archive leaderboard report
Link Prediction WN18RR RotatE Hits@10 0.571 #36 of 75 Archive leaderboard report
Link Prediction WN18RR RotatE Hits@3 0.492 #36 of 75 Archive leaderboard report
Link Prediction WN18RR RotatE MR 3340 #36 of 75 Archive leaderboard report
Link Prediction WN18RR RotatE MRR 0.476 #36 of 75 Archive leaderboard report
Link Prediction WN18RR pRotatE Hits@1 0.417 #50 of 75 Archive leaderboard report
Link Prediction WN18RR pRotatE Hits@10 0.552 #50 of 75 Archive leaderboard report
Link Prediction WN18RR pRotatE Hits@3 0.479 #50 of 75 Archive leaderboard report
Link Prediction WN18RR pRotatE MR 2923 #50 of 75 Archive leaderboard report
Link Prediction WN18RR pRotatE MRR 0.462 #50 of 75 Archive leaderboard report
Link Property Prediction ogbl-biokg RotatE Ext. data No #15 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg RotatE Number of params 187597000 #15 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg RotatE Test MRR 0.7989 ± 0.0004 #15 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg RotatE Validation MRR 0.7997 ± 0.0002 #15 of 16 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (250dim) Ext. data No #22 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (250dim) Number of params 1250435750 #22 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (250dim) Test MRR 0.4332 ± 0.0025 #22 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (250dim) Validation MRR 0.4353 ± 0.0028 #22 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (50dim) Ext. data No #30 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (50dim) Number of params 250087150 #30 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (50dim) Test MRR 0.2530 ± 0.0034 #30 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 RotatE (50dim) Validation MRR 0.2250 ± 0.0035 #30 of 30 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: RotatE

AdamRotatESelf-Adversarial Negative Sampling

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections