Scalable Learning of Entity and Predicate Embeddings for Knowledge Graph Completion
Open accessAbstract
Knowledge Graphs (KGs) are a widely used formalism for representing knowledge in the Web of Data. We focus on the problem of link prediction, i.e. predicting missing links in large knowledge graphs, so to discover new facts about the world. Representation learning models that embed entities and relation types in continuous vector spaces recently were used to achieve new state-of-the-art link prediction results. A limiting factor in these models is that the process of learning the optimal embedding vectors can be really time-consuming, and might even require days of computations for large KGs. In this work, we propose a principled method for sensibly reducing the learning time, while converging to more accurate link prediction models. Furthermore, we employ the proposed method for training and evaluating a set of novel and scalable models. Our extensive evaluations show significant improvements over state-of-the-art link prediction methods on several datasets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
KGE models can be effectively applied to link prediction.
“These models can be effectively applied to link prediction [14].”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [14]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 18
- K. D. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor, "Freebase: a collaboratively created graph database for structuring human knowledge," in Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, J. T. Wang, Ed. ACM, 2008, pp. 1247-1250.
- G. A. Miller, "Wordnet: A lexical database for english," Commun. ACM, vol. 38, no. 11, pp. 39-41, 1995.
- X. Dong, E. Gabrilovich, G. Heitz, W. Horn, N. Lao, K. Murphy, T. Strohmann, S. Sun, and W. Zhang, "Knowledge vault: a web-scale approach to probabilistic knowledge fusion," in The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '14, S. A. Macskassy et al., Eds. ACM, 2014, pp. 601-610.
- A. Bordes and E. Gabrilovich, "Constructing and mining web-scale knowledge graphs: KDD 2014 tutorial," in The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '14, 2014, p. 1967.
- Y. Bengio, A. C. Courville, and P. Vincent, "Representation learning: A review and new perspectives," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1798-1828, 2013.
- A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko, "Translating embeddings for modeling multi-relational data," in Ad- vances in Neural Information Processing Systems 26, C. Burges et al., Eds. Curran Associates, Inc., 2013, pp. 2787-2795.
- T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, "Distributed representations of words and phrases and their compo- sitionality," C. J. C. Burges et al., Eds., 2013, pp. 3111-3119.
- K. Chang, W. Yih, B. Yang, and C. Meek, "Typed tensor decomposition of knowledge bases for relation extraction," in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, A. Moschitti et al., Eds. ACL, 2014, pp. 1568-1579.
- A. Bordes, X. Glorot, J. Weston, and Y. Bengio, "A semantic matching energy function for learning with multi-relational data -application to word-sense disambiguation," Machine Learning, vol. 94, no. 2, pp. 233- 259, 2014.
- A. Bordes, J. Weston, R. Collobert, and Y. Bengio, "Learning structured embeddings of knowledge bases," in Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2011, W. Burgard et al., Eds. AAAI Press, 2011.
- R. Socher, D. Chen, C. D. Manning, and A. Ng, "Reasoning with neural tensor networks for knowledge base completion," in Advances in Neural Information Processing Systems 26, C. Burges et al., Eds. Curran Associates, Inc., 2013, pp. 926-934.
- M. Nickel, V. Tresp, and H. Kriegel, "A three-way model for collective learning on multi-relational data," in Proceedings of the 28th Interna- tional Conference on Machine Learning, ICML 2011, L. Getoor et al., Eds. Omnipress, 2011, pp. 809-816.
- R. Jenatton, N. L. Roux, A. Bordes, and G. R. Obozinski, "A latent factor model for highly multi-relational data," in Advances in Neural Information Processing Systems 25, F. Pereira et al., Eds. Curran Associates, Inc., 2012, pp. 3167-3175.
- Z. Wang, J. Zhang, J. Feng, and Z. Chen, "Knowledge graph embedding by translating on hyperplanes," in Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, C. E. Brodley et al., Eds. AAAI Press, 2014, pp. 1112-1119.
- D. E. Rumelhart, G. E. Hinton, and R. J. Wilson, "Learning repre- sentations by back-propagating errors," Nature, vol. 323, pp. 533-536, 1986.
- J. C. Duchi, E. Hazan, and Y. Singer, "Adaptive subgradient methods for online learning and stochastic optimization," Journal of Machine Learning Research, vol. 12, pp. 2121-2159, 2011.
- J. Dean, G. Corrado, R. Monga, K. Chen, M. Devin, M. Mao, M. A. Ranzato, A. Senior, P. Tucker, K. Yang, Q. V. Le, and A. Y. Ng, "Large scale distributed deep networks," in Advances in Neural Information Processing Systems 25, F. Pereira et al., Eds. Curran Associates, Inc., 2012, pp. 1223-1231.
- T. Schaul, I. Antonoglou, and D. Silver, "Unit tests for stochastic op- timization," in International Conference on Learning Representations, 2014.
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
- Minervini, P., Fanizzi, N., d'Amato, C., & Esposito, F.
- Affiliations
- University of Bari Aldo Moro (IT)
- Venue
- 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 162-167
- OpenAlex
- W2294137921
- Cited by
- 21
- References
- 0
- Citations by year
- 2024: 1 · 2023: 2 · 2022: 2 · 2021: 3 · 2020: 2 · 2019: 2 · 2018: 4 · 2017: 4 · 2016: 1
- FWCI
- 1.69
- Type
- conference paper
- Language
- en
- Open access
- green
- discovery.ucl.ac.uk
- Locations
- International Conference on Machine Learning and Applications (publishedVersion)
- UCL Discovery (University College London) (submittedVersion)
- CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro) (submittedVersion)
- Funders
- Ministero dell’Istruzione, dell’Università e della Ricerca
- 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 completion, link prediction, entity embeddings, relation embeddings, scalable learning, knowledge graph embedding, training time reduction
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
