Papers › A Benchmark for Semi-Inductive Link Prediction in Knowledge Graphs

A Benchmark for Semi-Inductive Link Prediction in Knowledge Graphs

18 Oct 2023arXiv:2310.11917archive 2025-07-28

Adrian Kochsiek, Rainer Gemulla

Semi-inductive link prediction (LP) in knowledge graphs (KG) is the task of predicting facts for new, previously unseen entities based on context information. Although new entities can be integrated by retraining the model from scratch in principle, such an approach is infeasible for large-scale KGs, where retraining is expensive and new entities may arise frequently. In this paper, we propose and describe a large-scale benchmark to evaluate semi-inductive LP models. The benchmark is based on and extends Wikidata5M: It provides transductive, k-shot, and 0-shot LP tasks, each varying the available information from (i) only KG structure, to (ii) including textual mentions, and (iii) detailed descriptions of the entities. We report on a small study of recent approaches and found that semi-inductive LP performance is far from transductive performance on long-tail entities throughout all experiments. The benchmark provides a test bed for further research into integrating context and textual information in semi-inductive LP models.

PaperPDFCode

Code

uma-pi1/wikidata5m-si officialmentioned 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Inductive Link PredictionKnowledge GraphsLink Prediction

Datasets

Introduced by this paper, per the archive.

Wikidata5M-SI

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Inductive Link Prediction Wikidata5M-SI KGT5 (descriptions) 0-shot MRR 0.470 #1 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI KGT5-context (descriptions) 0-shot MRR 0.417 #2 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI KGT5-context (descriptions) 1-shot MRR 0.420 #2 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI KGT5-context (descriptions) 10-shot MRR 0.437 #2 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI SimKGC (descriptions) 0-shot MRR 0.403 #3 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI KGT5 (mentions) 0-shot MRR 0.31 #4 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI SimKGC (mentions) 0-shot MRR 0.22 #5 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI ComplEx + Bias * FoldIn 0-shot MRR 0.124 #6 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI HittER 0-shot MRR 0.019 #7 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI HittER 1-shot MRR 0.105 #7 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI HittER 10-shot MRR 0.221 #7 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI DistMult + ERAvg (descriptions) 1-shot MRR 0.278 #8 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI DistMult + ERAvg (descriptions) 10-shot MRR 0.292 #8 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI KGT5-context (mentions) 1-shot MRR 0.217 #9 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI KGT5-context (mentions) 10-shot MRR 0.311 #9 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI DistMult + ERAvg (mentions) 1-shot MRR 0.187 #10 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI DistMult + ERAvg (mentions) 10-shot MRR 0.28 #10 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI DistMult + ERAvg 1-shot MRR 0.171 #11 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI DistMult + ERAvg 10-shot MRR 0.333 #11 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI ComplEx + Bias + Fold in 1-shot MRR 0.151 #12 of 12 Archive leaderboard report
Inductive Link Prediction Wikidata5M-SI ComplEx + Bias + Fold in 10-shot MRR 0.206 #12 of 12 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