AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion

Kunxun Qi, Jianfeng Du, Hai Wan

NeurIPS 2023 · Graph learning › Knowledge and temporal graphs · approach: Inductive knowledge graph completion · 1 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
add soft triples to background KG (ablation)LSTK-TELM · HacREDMRR: 0.416 -> 0.734Improved
add soft triples to background KG (ablation)LSTK-TELM · BioRelMRR: 0.339 -> 0.600Improved
add textual copy rules (soft triple for each hard triple) (ablation)LSTK-TELM · BioRelMRR: 0.511 -> 0.600Improved
add textual copy rules (ablation)LSTK-TELM · HacREDMRR: 0.710 -> 0.734Improved
allow textual relations in TE-rules (ablation)LSTK-TELM · HacREDMRR: 0.579 -> 0.734Improved
allow textual relations in TE-rules (ablation)LSTK-TELM · BioRelMRR: 0.356 -> 0.600Improved
add disjunctive atoms in TE-rules (ablation)LSTK-TELM · DocREDMRR: 0.453 -> 0.514Improved
use entailment-probability confidence scores instead of fixed 1.0 (ablation)LSTK-TELM · BioRelMRR: 0.574 -> 0.600Improved
textual entailment model instead of BERT relation extraction for soft triples (ablation)LSTK-TELM · BioRelMRR: 0.572 -> 0.600Improved
add soft triples (LSTK-X dagger) without textual relations in rulesDRUM · HacREDMRR: 0.387 -> 0.347Hurt
add soft triples (LSTK-X dagger) without textual relations in rulesNeuralLP · HacREDMRR: 0.395 -> 0.320Hurt
allow textual relations in learnt rules (LSTK-X vs LSTK-X dagger)DRUM · HacREDMRR: 0.347 -> 0.538Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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