Papers › Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion

Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion

11 Nov 2020NeurIPS 2020 12arXiv:2011.05816archive 2025-07-28

Zhanqiu Zhang, Jianyu Cai, Jie Wang

Tensor factorization based models have shown great power in knowledge graph completion (KGC). However, their performance usually suffers from the overfitting problem seriously. This motivates various regularizers -- such as the squared Frobenius norm and tensor nuclear norm regularizers -- while the limited applicability significantly limits their practical usage. To address this challenge, we propose a novel regularizer -- namely, DUality-induced RegulArizer (DURA) -- which is not only effective in improving the performance of existing models but widely applicable to various methods. The major novelty of DURA is based on the observation that, for an existing tensor factorization based KGC model (primal), there is often another distance based KGC model (dual) closely associated with it. Experiments show that DURA yields consistent and significant improvements on benchmarks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2011.05816")

Code

Syntology Ran 0 of 2 code samples harvested from 1 repository linked to this paper; 2 have no recorded run.

By repository: official repository: 2 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.

MIRALab-USTC/KGE-DURA officialmentioned in papermentioned on GitHubpytorch report
MIRALab-USTC/KGE-HAKE mentioned on GitHubpytorch report
miralab-ustc/qe-cone mentioned on GitHubpytorch 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

2 samples harvested; 0 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2unverified

Licence: 2 of the 2 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 MIRALab-USTC/KGE-DURA. “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.

DURA MIRALab-USTC/KGE-DURA/code/regularizers.py official repository unverified no licence file found · pointer only · b3941f51059c203e · report
Regularizer MIRALab-USTC/KGE-DURA/code/regularizers.py official repository unverified no licence file found · pointer only · 2506c17cda0c5069 · report

Tasks

Knowledge Graph CompletionLink Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB15k-237 ComplEx-DURA Hits@1 0.276 #10 of 75 Archive leaderboard report
Link Prediction FB15k-237 ComplEx-DURA Hits@10 0.560 #10 of 75 Archive leaderboard report
Link Prediction FB15k-237 ComplEx-DURA MRR 0.371 #10 of 75 Archive leaderboard report
Link Prediction WN18RR RESCAL-DURA Hits@1 0.455 #33 of 75 Archive leaderboard report
Link Prediction WN18RR RESCAL-DURA Hits@10 0.577 #33 of 75 Archive leaderboard report
Link Prediction WN18RR RESCAL-DURA MRR 0.498 #33 of 75 Archive leaderboard report
Link Prediction WN18RR CP-DURA Hits@1 0.441 #51 of 75 Archive leaderboard report
Link Prediction WN18RR CP-DURA Hits@10 0.552 #51 of 75 Archive leaderboard report
Link Prediction WN18RR CP-DURA MRR 0.478 #51 of 75 Archive leaderboard report
Link Prediction WN18RR ComplEx-DURA Hits@1 0.449 #73 of 75 Archive leaderboard report
Link Prediction WN18RR ComplEx-DURA MRR 0.491 #73 of 75 Archive leaderboard report
Link Prediction YAGO3-10 ComplEx-DURA (large model) Hits@1 0.511 #2 of 18 Archive leaderboard report
Link Prediction YAGO3-10 ComplEx-DURA (large model) Hits@10 0.713 #2 of 18 Archive leaderboard report
Link Prediction YAGO3-10 ComplEx-DURA (large model) MRR 0.584 #2 of 18 Archive leaderboard report
Link Prediction YAGO3-10 CP-DURA (large model) Hits@1 0.506 #3 of 18 Archive leaderboard report
Link Prediction YAGO3-10 CP-DURA (large model) Hits@10 0.709 #3 of 18 Archive leaderboard report
Link Prediction YAGO3-10 CP-DURA (large model) MRR 0.579 #3 of 18 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.

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