Learning Knowledge Graph Embeddings with Type Regularizer
Abstract
Learning relations based on evidence from knowledge repositories rely on processing the available relation instances. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form of a regularization factor added to the loss function that takes into account the types (categories) of the entities that appear as arguments to relations in the knowledge base. Tested on Freebase, a frequently used benchmarking dataset for link/path predicting tasks, we note increased performance compared to the baseline model in terms of mean reciprocal rank and [email protected], N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Bilinear+TR improves RESCAL by introducing a regularization factor into the loss function to take entity types into account.
“Bilinear+TR [78] improves RESCAL [64] by introducing a regularization factor into the loss function, which is used to take entity types into account.”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [78]
For Bilinear+TR and LiteralE, adding entity type, text and other information helps to improve performance.
“In terms of Bilinear+TR [78] and LiteralE [115], we can see that adding the entity type, text and other information helps to improve performance.”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [78]
Cited by
Sorted by citations
A Survey on Knowledge Graph Embeddings for Link Prediction
Wang, M., Qiu, L., & Wang, X. (2021) · Symmetry · doi:10.3390/sym13030485 · Cited by 212 · see citing works
- Authors
- Kotnis, B., & Nastase, V.
- Affiliations
- Heidelberg University (DE)
- Heidelberg University, Heidelberg, Germany
- ORCID
- Kotnis, Bhushan
- Venue
- Proceedings of the Knowledge Capture Conference
- Publisher
- ACM
- Published
- 2017-12-04
- Pages
- 1-4
- OpenAlex
- W2731439883
- Cited by
- 3
- References
- 0
- Citations by year
- 2021: 1 · 2019: 1 · 2018: 1
- FWCI
- 0.25
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Knowledge Capture (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- knowledge graph embedding, entity types, regularization, link prediction, trajectory prediction, Freebase
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
