Papers › Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph...

Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings

11 Jul 2022arXiv:2207.04979archive 2025-07-28

Adrian Kochsiek, Fritz Niesel, Rainer Gemulla

Knowledge graph embedding (KGE) models are an effective and popular approach to represent and reason with multi-relational data. Prior studies have shown that KGE models are sensitive to hyperparameter settings, however, and that suitable choices are dataset-dependent. In this paper, we explore hyperparameter optimization (HPO) for very large knowledge graphs, where the cost of evaluating individual hyperparameter configurations is excessive. Prior studies often avoided this cost by using various heuristics; e.g., by training on a subgraph or by using fewer epochs. We systematically discuss and evaluate the quality and cost savings of such heuristics and other low-cost approximation techniques. Based on our findings, we introduce GraSH, an efficient multi-fidelity HPO algorithm for large-scale KGEs that combines both graph and epoch reduction techniques and runs in multiple rounds of increasing fidelities. We conducted an experimental study and found that GraSH obtains state-of-the-art results on large graphs at a low cost (three complete training runs in total).

PaperPDFCode

Code

uma-pi1/grash officialmentioned in papermentioned on GitHubpytorch report
uma-pi1/dist-kge 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

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

Tasks

Graph EmbeddingHyperparameter OptimizationKnowledge Graph EmbeddingKnowledge Graph EmbeddingsKnowledge GraphsLink Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction YAGO3-10 ComplEx MRR 0.551 #18 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.

Methods

HPO

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