CoChat
Sign Up
Cited by 132Advanced Graph Neural NetworksTopic ModelingSemantic Web and Ontologies

Embedding Uncertain Knowledge Graphs

Open access
Chen, Xuelu, Chen, Muhao, Shi, Weijia, Sun, Yizhou, Zaniolo, Carlo·2019·Proceedings of the AAAI Conference on Artificial Intelligence
DOI 10.1609/aaai.v33i01.33013363
Open this paper in CoChat — free account

Abstract

Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge they contain into machine learning. However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents an unresolved challenge. The capturing of uncertain knowledge will benefit many knowledge-driven applications such as question answering and semantic search by providing more natural characterization of the knowledge. In this paper, we propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space. Unlike previous models that characterize relation facts with binary classification techniques, UKGE learns embeddings according to the confidence scores of uncertain relation facts. To further enhance the precision of UKGE, we also introduce probabilistic soft logic to infer confidence scores for unseen relation facts during training. We propose and evaluate two variants of UKGE based on different confidence score modeling strategies. Experiments are conducted on three real-world uncertain KGs via three tasks, i.e. confidence prediction, relation fact ranking, and relation fact classification. UKGE shows effectiveness in capturing uncertain knowledge by achieving promising results, and it consistently outperforms baselines on these tasks.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1609/aaai.v33i01.33013363

Cites

4 of 4 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Existing UKG embedding approaches model entities and relations as points in low-dimensional vector space.

    “existing approaches model entities and relations as points in low-dimensional vector space, measure triple plausibility with vector similarity (eg.distance, dot-product), and map the plausibility to the confidence range of [0,1].”

    From Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021) · cites this paper as Chen et al., 2019

    The Related Work section (p. 2) says that, to the authors’ knowledge, no previous work had learned embeddings for uncertain KGs, contrary to the claim about existing UKG embedding approaches. It describes earlier deterministic KG models as encoding entities as low-dimensional vectors and relations as algebraic operations, rather than both as points. The plausibility-to-confidence mapping appears in the description of the paper’s proposed model (Section 4.1, p. 3). (LLM, conf=0.87)

    Checked by a reasoning model — may be wrong.

    Experimental — accuracy not yet measured

  • Existing UKG embedding approaches measure triple plausibility with vector similarity (e.g., distance, dot-product).

    “existing approaches model entities and relations as points in low-dimensional vector space, measure triple plausibility with vector similarity (eg.distance, dot-product), and map the plausibility to the confidence range of [0,1].”

    From Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021) · cites this paper as Chen et al., 2019

    Section 4.1 (p. 3) models triple plausibility using an inner product of embeddings and maps that plausibility to a confidence score, supporting the description of this paper’s UKGE method. But Related Work (p. 2) says there had been no previous work on embedding uncertain KGs, and Relation Fact Ranking (p. 6) says the earlier deterministic models do not encode confidence scores. The paper therefore does not support describing the full procedure as characteristic of existing UKG embedding approaches generally. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • Following Chen et al. (2019), only facts with confidence above the threshold τ = 0.85 were used to train deterministic models.

    “Following Chen et al. (2019), we only use facts with confidence above the threshold τ = 0.85 to train deterministic models.”

    From Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021) · cites this paper as Chen et al. (2019)

    Section 5.4 (pp. 5–6) says the deterministic baseline models were trained using only high-confidence relation facts, selected with a KG-specific threshold τ. Section 5.7 (p. 7) defines a strong fact as one whose confidence exceeds that threshold. Our copy does not establish τ = 0.85 as the threshold, so the numerical part of the attribution is unsupported. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • UKGE models triple plausibility in the form of embedding product.

    “the representative work UKGE (Chen et al., 2019) models the triple plausibility in the form of embedding product (Yang et al., 2015), and trains the embedding model as a regressor to predict the confidence score.”

    From Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021) · cites this paper as Chen et al., 2019

  • Existing UKG embedding approaches map plausibility to the confidence range [0,1].

    “existing approaches model entities and relations as points in low-dimensional vector space, measure triple plausibility with vector similarity (eg.distance, dot-product), and map the plausibility to the confidence range of [0,1].”

    From Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021) · cites this paper as Chen et al., 2019

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

Flagged first, then by citations

Research works printed but not linked: 29

  1. [Bach et al. 2017] Bach, S. H.; Broecheler, M.; Huang, B.; and Getoor, L. 2017. Hinge-loss markov random fields and probabilistic soft logic. JMLR .
  2. [Bollacker et al. 2008] Bollacker, K.; Evans, C.; Paritosh, P.; Sturge, T.; and Taylor, J. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In SIGMOD .
  3. [Bordes et al. 2013] Bordes, A.; Usunier, N.; Garcia-Duran, A.; Weston, J.; and Yakhnenko, O. 2013. Translating embeddings for modeling multi-relational data. In NIPS .
  4. [Bordes, Weston, and Usunier 2014] Bordes, A.; Weston, J.; and Usunier, N. 2014. Open question answering with weakly supervised embedding models. In ECML-PKDD . Springer.
  5. [Chen et al. 2015] Chen, M.; Weinberger, K. Q.; Xu, Z.; and Sha, F. 2015. Marginalizing stacked linear denoising autoencoders. JMLR .
  6. [Das et al. 2018] Das, R.; Dhuliawala, S.; Zaheer, M.; Vilnis, L.; Durugkar, I.; Krishnamurthy, A.; Smola, A.; and McCallum, A. 2018. Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. In ICLR .
  7. [Dettmers et al. 2018] Dettmers, T.; Minervini, P.; Stenetorp, P.; and Riedel, S. 2018. Convolutional 2d knowledge graph embeddings. In AAAI .
  8. [Duchi, Hazan, and others 2011] Duchi, J.; Hazan, E.; et al. 2011. Adaptive subgradient methods for online learning and stochastic optimization. JMLR 12(Jul).
  9. [He et al. 2017] He, H.; Balakrishnan, A.; Eric, M.; and Liang, P. 2017. Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings. In ACL .
  10. [Hu et al. 2017] Hu, J.; Cheng, R.; Huang, Z.; Fang, Y.; and Luo, S. 2017. On embedding uncertain graphs. In CIKM .
  11. [Jenatton et al. 2012] Jenatton, R.; Roux, N. L.; Bordes, A.; and Obozinski, G. R. 2012. A latent factor model for highly multirelational data. In NIPS .
  12. [Ji et al. 2015] Ji, G.; He, S.; Xu, L.; Liu, K.; and Zhao, J. 2015. Knowledge graph embedding via dynamic mapping matrix. In ACL .
  13. [Jia et al. 2016] Jia, Y.; Wang, Y.; Lin, H.; Jin, X.; and Cheng, X. 2016. Locally adaptive translation for knowledge graph embedding. In AAAI , 992-998.
  14. [Kadlec, Bajgar, and Kleindienst 2017] Kadlec, R.; Bajgar, O.; and Kleindienst, J. 2017. Knowledge base completion: Baselines strike back. In ACL .
  15. [Kimmig et al. 2012] Kimmig, A.; Bach, S.; Broecheler, M.; Huang, B.; and Getoor, L. 2012. A short introduction to probabilistic soft logic. In Proceedings of the NIPS Workshop on Probabilistic Programming: Foundations and Applications , 1-4.
  16. [Lin et al. 2015] Lin, Y.; Liu, Z.; Sun, M.; Liu, Y.; and Zhu, X. 2015. Learning entity and relation embeddings for knowledge graph completion. In AAAI .
  17. [Mitchell et al. 2018] Mitchell, T.; Cohen, W.; Hruschka, E.; Talukdar, P.; Yang, B.; Betteridge, J.; Carlson, A.; Dalvi, B.; Gardner, M.; Kisiel, B.; et al. 2018. Never-ending learning. Communications of the ACM .
  18. [Nickel, Rosasco, and Poggio 2016] Nickel, M.; Rosasco, L.; and Poggio, T. 2016. Holographic embeddings of knowledge graphs. In AAAI .
  19. [Nickel, Tresp, and Kriegel 2011] Nickel, M.; Tresp, V.; and Kriegel, H.-P. 2011. A three-way model for collective learning on multi-relational data. In ICML .
  20. [Pujara, Augustine, and Getoor 2017] Pujara, J.; Augustine, E.; and Getoor, L. 2017. Sparsity and noise: Where knowledge graph embeddings fall short. In EMNLP .
  21. [Shi and Weninger 2017] Shi, B., and Weninger, T. 2017. Proje: Embedding projection for knowledge graph completion. In AAAI .
  22. [Socher et al. 2013] Socher, R.; Chen, D.; Manning, C. D.; and Ng, A. 2013. Reasoning with neural tensor networks for knowledge base completion. In NIPS .
  23. [Wang and Wang 2016] Wang, Z., and Wang, H. 2016. Understanding short texts. In ACL .
  24. [Wang et al. 2014] Wang, Z.; Zhang, J.; Feng, J.; and Chen, Z. 2014. Knowledge graph embedding by translating on hyperplanes. In AAAI .
  25. [Wang et al. 2015] Wang, Z.; Wang, H.; Wen, J.-R.; and Xiao, Y. 2015. An inference approach to basic level of categorization. In CIKM .
  26. [Weston, Bordes, and others 2013] Weston, J.; Bordes, A.; et al. 2013. Connecting language and knowledge bases with embedding models for relation extraction. In EMNLP .
  27. [Wu et al. 2012] Wu, W.; Li, H.; Wang, H.; and Zhu, K. Q. 2012. Probase: A probabilistic taxonomy for text understanding. In SIGMOD .
  28. [Yang et al. 2015] Yang, B.; Yih, W.-t.; He, X.; Gao, J.; and Deng, L. 2015. Embedding entities and relations for learning and inference in knowledge bases. ICLR .
  29. [Yih et al. 2013] Yih, W.-t.; Chang, M.-W.; Meek, C.; and Pastusiak, A. 2013. Question answering using enhanced lexical semantic models. In ACL .

Cited by

Sorted by citations

Authors
Chen, X., Chen, M., Shi, W., Sun, Y., & Zaniolo, C.
Affiliations
University of California, Los Angeles (US)
ORCID
Venue
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Published
2019-07-17
Volume
33
Issue
01
Pages
3363-3370
ISSN
  • 2159-5399 (ISSN-L)
  • 2374-3468
DOI
10.1609/aaai.v33i01.33013363
OpenAlex
W2963149704
Cited by
132
References
4
Citations by year
2026: 16 · 2025: 11 · 2024: 27 · 2023: 25 · 2022: 20 · 2021: 17 · 2020: 14 · 2019: 2
FWCI
5.07
Type
conference paper
Language
en
Open access
Licence
www.aaai.org/ (unspecified)
Locations
  • Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Science Foundation (1741634, CAREER, 1705169)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Semantic Web and Ontologies
Keywords
knowledge graph embedding, confidence scores, probabilistic soft logic, confidence estimation, uncertainty modeling

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