Abstract
Identifying and repairing the erroneous and missing information in the graphs is crucial. Rule-based studies rely on graph quality rules to detect the inconsistencies among different entities and make a one-time repair to resolve these inconsistencies. The missing data can be predicted and imputed by graph embedding methods by preserving the inherent structure of a reliable graph. However, both lines of way need more evidence to improve. In this paper, we propose Grier, a novel repairing method to enrich the evidence by taking advantage of rule-based repairing and graph embedding. Specifically, Grier iteratively learns the graph embeddings with guidance from logical rules, which has significant power in knowledge acquisition and inference. The erroneous triples are detected and repaired by evaluating the correctness of the triples in the embedding space. The newly repaired triples are used as training data to update the embedding module for better learning. Extensive experiments on three graphs demonstrate the effectiveness of Grier even with very few rules.
Similar content being viewed by others
Notes
In this paper, we restrict the logical rules to be Horn clause rules, where the premise of each rule contains a set of clauses and the conclusion of each rule contains only one clause.
AMIE3 provides two types of confidence, i.e., standard confidence and PCA confidence. In this paper, we use PCA confidence.
References
Bai L, Wang J, Zhu L (2022) Fixing the inconsistencies of continuous changing operations in fuzzy spatiotemporal RDF graph. Appl Soft Comput 131:109767
Bordes A, Usunier N, García-Durán A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. In: Proceedings of the NIPS, pp 2787–2795
Cheng K, Yang Z, Zhang M, Sun Y (2021) Uniker: a unified framework for combining embedding and definite horn rule reasoning for knowledge graph inference. In: Proceedings of the EMNLP, pp 9753–9771
Cheng Y, Chen L, Yuan Y, Wang G (2018) Rule-based graph repairing: semantic and efficient repairing methods. In: Proceedings of ICDE, pp 773–784
Cheng Y, Chen L, Yuan Y, Wang G, Li B, Jin F (2022) Strict and flexible rule-based graph repairing. IEEE Trans Knowl Data Eng 34(7):3521–3535
Dettmers T, Minervini P, Stenetorp P, Riedel S (2018) Convolutional 2D knowledge graph embeddings. In: Proceedings of AAAI, pp 1811–1818
Ding B, Wang Q, Wang B, Guo L (2018) Improving knowledge graph embedding using simple constraints. In: Proceedings of ACL, pp 110–121
Dong X, Gabrilovich E, Heitz G, Horn W, Lao N, Murphy K, Strohmann T, Sun S, Zhang W (2014) Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: Proceedings of KDD, pp 601–610
Fan W, Liu X, Lu P, Tian C (2018) Catching numeric inconsistencies in graphs. In: Proceedings of SIGMOD, pp 381–393
Fan W, Lu P (2019) Dependencies for graphs. ACM Trans Database Syst 44(2):5:1-5:40
Fan W, Wu Y, Xu J (2016) Functional dependencies for graphs. In: Proceedings of SIGMOD, pp 1843–1857
Fang H, Wang Y, Tian Z, Ye Y (2023) Learning knowledge graph embedding with a dual-attention embedding network. Expert Syst Appl 212:118806
Gaur G, Dang A, Bhattacharya A, Bedathur S (2021) Computing and maintaining provenance of query result probabilities in uncertain knowledge graphs. In: Proceedings of CIKM, pp 545–554
Ge C, Gao Y, Weng H, Zhang C, Miao X, Zheng B (2020) Kgclean: An embedding powered knowledge graph cleaning framework. arXiv
Guo S, Li L, Hui Z, Meng L, Ma B, Liu W, Wang L, Zhai H, Zhang H (2020) Knowledge graph embedding preserving soft logical regularity. In: Proceedings of CIKM, pp 425–434
Guo S, Wang Q, Wang L, Wang B, Guo L (2016) Jointly embedding knowledge graphs and logical rules. In: Proceedings of EMNLP, pp 192–202
Guo S, Wang Q, Wang L, Wang B, Guo L (2018) Knowledge graph embedding with iterative guidance from soft rules. In: Proceedings of AAAI, pp 4816–4823
Ha J, Pyo H, Kim J (2016) Large-scale item categorization in e-commerce using multiple recurrent neural networks. In: Proceedings of SIGKDD, pp 107–115
Ho VT, Stepanova D, Gad-Elrab MH, Kharlamov E, Weikum G (2018) Rule learning from knowledge graphs guided by embedding models. In: Proceedings of ISWC, vol 11136, pp 72–90
Ji G, He S, Xu L, Liu K, Zhao J (2015) Knowledge graph embedding via dynamic mapping matrix. In: Proceedings of ACL, pp 687–696
Kemp C, Tenenbaum JB, Griffiths TL, Yamada T, Ueda N (2006) Learning systems of concepts with an infinite relational model. In: Proceedings of AAAI, pp 381–388
Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceedings of EMNLP, pp 1746–1751
Kwashie S, Liu J, Li J, Liu L, Stumptner M, Yang L (2019) Certus: an effective entity resolution approach with graph differential dependencies (GDDs). PVLDB 12(6):653–666
Lajus J, Galárraga L, Suchanek F (2020) Fast and exact rule mining with AMIE 3. In: Proceedings of ESWC, pp 36–52
Lin Y, Liu Z, Sun M, Liu Y, Zhu X (2015) Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of AAAI, pp 2181–2187
Manipur I, Manzo M, Granata I, Giordano M, Maddalena L, Guarracino MR (2022) Netpro2vec: a graph embedding framework for biomedical applications. IEEE ACM Trans Comput Biol Bioinform 19(2):729–740
Mishra A, Laha A, Sankaranarayanan K, Jain P, Krishnan S (2019) Storytelling from structured data and knowledge graphs: an NLG perspective. In: Proceedings of ACL, pp 43–48
Nathani D, Chauhan J, Sharma C, Kaul M (2019) Learning attention-based embeddings for relation prediction in knowledge graphs. In: Proceedings of ACL, pp 4710–4723
Nguyen DQ, Nguyen DQ, Nguyen TD, Phung D (2019) A convolutional neural network-based model for knowledge base completion and its application to search personalization. Semant Web 10(5):947–960
Qu M, Tang J (2019) Probabilistic logic neural networks for reasoning. In: Proceedings of NeurIPS, pp 7710–7720
Raedt LD, Kersting K (2008) Probabilistic inductive logic programming. In: Probabilistic inductive logic programming—theory and applications, volume 4911 of lecture notes in computer science. Springer, pp 1–27
Richardson M, Domingos PM (2006) Markov logic networks. Mach Learn 62(1–2):107–136
Safavi T, Koutra D (2020) Codex: a comprehensive knowledge graph completion benchmark. In: Proceedings of EMNLP, pp 8328–8350
Shi B, Weninger T (2018) Open-world knowledge graph completion. In: Proceedings of AAAI, pp 1957–1964
Singla P, Domingos P (2005) Discriminative training of Markov logic networks. In: Proceedings of AAAI, vol 5, pp 868–873
Song Q, Wu Y, Lin P, Dong X, Sun H (2018) Mining summaries for knowledge graph search. IEEE Trans Knowl Data Eng 30(10):1887–1900
Toutanova K, Chen D (2015) Observed versus latent features for knowledge base and text inference. In: Proceedings of ACL, pp 57–66
Trouillon T, Welbl J, Riedel S, Gaussier É, Bouchard G (2016) Complex embeddings for simple link prediction. In: Proceedings of ICML, pp 2071–2080
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: Proceedings of AAAI
Yang B, Yih W, He X, Gao J, Deng L (2015) Embedding entities and relations for learning and inference in knowledge bases. In: Proceedings of ICLR
Zhao S, Qin B, Liu T, Wang F (2020) Biomedical knowledge graph refinement with embedding and logic rules. arXiv
Acknowledgements
This paper was partially supported by Natural Science Foundation of Zhejiang Province (No. LQ22F020032), National Natural Science Foundation of China (No. 62202132), and National Key Research and Development Program of China (No. 2022YFE0199300)
Author information
Authors and Affiliations
Contributions
CY involved in methodology, software, validation, formal analysis, writing—original draft and visualization; HX involved in software, data curation and visualization; HZ and YW involved in conceptualization, resources, writing—review and editing, supervision, project administration and funding acquisition; GD involved in resources and funding acquisition.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ye, C., Xu, H., Zhang, H. et al. Grier: graph repairing based on iterative embedding and rules. Knowl Inf Syst 65, 3273–3294 (2023). https://doi.org/10.1007/s10115-023-01866-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-023-01866-x