AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs

Ali Sadeghian, Mohammadreza Armandpour, Patrick Ding, Daisy Zhe Wang

NeurIPS 2019 · Graph learning › Knowledge and temporal graphs · approach: Logical query answering and rule reasoning · 61 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use rank 4 instead of rank 1 for rule-confidence estimation (ablation)DRUM · Family, UMLS, and Kinship (T=2 and T=3)MRR: Family T=2: .92 -> .94; UMLS T=2: .80 -> .81; Kinship T=2: .51 -> .60; Family T=3: .91 -> .95; UMLS T=3: .77 -> .80; KinImproved
use maximum rule length 3 instead of 2 (ablation)DRUM · WN18RR transductiveMRR: .435 -> .486Improved
use maximum rule length 3 instead of 2 (ablation)DRUM · FB15K-237 transductiveMRR: .250 -> .343Improved
use maximum rule length 3 instead of 2 (ablation)DRUM · Family, UMLS, and KinshipMRR: Family: .94 -> .95; UMLS: .81 -> .80; Kinship: .60 -> .61Mixed
use DRUM instead of Neural LPlink prediction · WN18RR transductiveMRR: .435 -> .486Improved
use DRUM instead of Neural LPlink prediction · FB15K-237 transductiveMRR: .24 -> .343Improved
use DRUM instead of Neural LPinductive link prediction · WN18Hits@10: 94.49 -> 95.21Improved
use DRUM instead of Neural LPinductive link prediction · FB15K-237Hits@10: 27.97 -> 29.13Improved
use DRUM instead of Neural LPrule mining · Family human rule assessment: father, sister, and unclenumber of consecutive correct rules: father: 2 -> 5; sister: 3 -> 10; uncle: 6 -> 6Mixed
use the rank-one confidence estimator instead of the higher-rank DRUM estimator (ablation)rule-confidence estimation · logical rule qualityincorrect high-confidence rulesHurt

Later papers that compared with this method

6 later accepted papers report DruM as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy