Assessing the effects of hyperparameters on knowledge graph embedding quality

Oliver Lloyd*, Tom R Gaunt, Yi Liu

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)peer-review

1 Citation (Scopus)
32 Downloads (Pure)

Abstract

Embedding knowledge graphs into low-dimensional spaces is a popular method for applying approaches, such as link prediction or node classification, to these databases. This embedding process is very costly in terms of both computational time and space. Part of the reason for this is the optimisation of hyperparameters, which involves repeatedly sampling, by random, guided, or brute-force selection, from a large hyperparameter space and testing the resulting embeddings for their quality. However, not all hyperparameters in this search space will be equally important. In fact, with prior knowledge of the relative importance of the hyperparameters, some could be eliminated from the search altogether without significantly impacting the overall quality of the outputted embeddings. To this end, we ran a Sobol sensitivity analysis to evaluate the effects of tuning different hyperparameters on the variance of embedding quality. This was achieved by performing thousands of embedding trials, each time measuring the quality of embeddings produced by different hyperparameter configurations. We regressed the embedding quality on those hyperparameter configurations, using this model to generate Sobol sensitivity indices for each of the hyperparameters. By evaluating the correlation between Sobol indices, we find substantial variability in the hyperparameter sensitivities between knowledge graphs with differing dataset characteristics as the probable cause of these inconsistencies. As an additional contribution of this work we identify several relations in the UMLS knowledge graph that may cause data leakage via inverse relations, and derive and present UMLS-43, a leakage-robust variant of that graph.
Original languageEnglish
Article number59
JournalJournal of Big Data
Volume10
Issue number1
DOIs
Publication statusPublished - 6 May 2023

Bibliographical note

Funding Information:
This work was supported by the UK Medical Research Council (MRC) and carried out in the MRC Integrative Epidemiology Unit [MC_UU_00011/4].

Publisher Copyright:
© 2023, The Author(s).

Fingerprint

Dive into the research topics of 'Assessing the effects of hyperparameters on knowledge graph embedding quality'. Together they form a unique fingerprint.

Cite this