Papers
Topics
Authors
Recent
Search
2000 character limit reached

Extending Complex Logical Queries on Uncertain Knowledge Graphs

Published 3 Mar 2024 in cs.AI | (2403.01508v2)

Abstract: The study of machine learning-based logical query answering enables reasoning with large-scale and incomplete knowledge graphs. This paper advances this area of research by addressing the uncertainty inherent in knowledge. While the uncertain nature of knowledge is widely recognized in the real world, it does not align seamlessly with the first-order logic that underpins existing studies. To bridge this gap, we explore the soft queries on uncertain knowledge, inspired by the framework of soft constraint programming. We propose a neural symbolic approach that incorporates both forward inference and backward calibration to answer soft queries on large-scale, incomplete, and uncertain knowledge graphs. Theoretical discussions demonstrate that our method avoids catastrophic cascading errors in the forward inference while maintaining the same complexity as state-of-the-art symbolic methods for complex logical queries. Empirical results validate the superior performance of our backward calibration compared to extended query embedding methods and neural symbolic approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Adams, E. W. A primer of probability logic. 1996.
  2. Neural Methods for Logical Reasoning over Knowledge Graphs. October 2021. URL https://openreview.net/forum?id=tgcAoUVHRIB.
  3. Leveraging linguistic structure for open domain information extraction. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp.  344–354, 2015.
  4. Complex Query Answering with Neural Link Predictors. In International Conference on Learning Representations, 2021.
  5. Adapting Neural Link Predictors for Complex Query Answering, January 2023. URL http://arxiv.org/abs/2301.12313. arXiv:2301.12313 [cs].
  6. Query2Particles: Knowledge Graph Reasoning with Particle Embeddings. In Findings of the Association for Computational Linguistics: NAACL 2022, pp.  2703–2714, 2022.
  7. Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization. In Proceedings of the 40th International Conference on Machine Learning, pp.  1472–1491. PMLR, July 2023. URL https://proceedings.mlr.press/v202/bai23b.html. ISSN: 2640-3498.
  8. Semiring-based csps and valued csps: Frameworks, properties, and comparison. Constraints, 4:199–240, 1999.
  9. Translating Embeddings for Modeling Multi-relational Data. In Advances in Neural Information Processing Systems, volume 26. Curran Associates, Inc., 2013. URL https://papers.nips.cc/paper_files/paper/2013/hash/1cecc7a77928ca8133fa24680a88d2f9-Abstract.html.
  10. Supply chain link prediction on uncertain knowledge graph. SIGKDD Explor., 24(2):124–130, 2022. doi: 10.1145/3575637.3575655. URL https://doi.org/10.1145/3575637.3575655.
  11. Toward an architecture for never-ending language learning. In Proceedings of the AAAI conference on artificial intelligence, volume 24, pp.  1306–1313, 2010.
  12. The theory of probabilistic databases. In VLDB, volume 87, pp.  1–4, 1987.
  13. Open-world probabilistic databases: Semantics, algorithms, complexity. Artificial Intelligence, 295:103474, 2021.
  14. Chen, J. Learning Language Representations with Logical Inductive Bias, February 2023. URL http://arxiv.org/abs/2302.09458. arXiv:2302.09458 [cs].
  15. Embedding uncertain knowledge graphs. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pp.  3363–3370, 2019.
  16. Probabilistic box embeddings for uncertain knowledge graph reasoning. arXiv preprint arXiv:2104.04597, 2021a.
  17. Fuzzy logic based logical query answering on knowledge graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pp.  3939–3948, 2022. Issue: 4.
  18. Passleaf: A pool-based semi-supervised learning framework for uncertain knowledge graph embedding. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5):4019–4026, May 2021b. doi: 10.1609/aaai.v35i5.16522. URL https://ojs.aaai.org/index.php/AAAI/article/view/16522.
  19. Probabilistic entity representation model for reasoning over knowledge graphs. Advances in Neural Information Processing Systems, 34:23440–23451, 2021.
  20. Embedding logical queries on knowledge graphs. Advances in neural information processing systems, 31, 2018.
  21. Liang, S. Knowledge graph embedding based on graph neural network. In 2023 IEEE 39th International Conference on Data Engineering (ICDE), pp.  3908–3912, April 2023. doi: 10.1109/ICDE55515.2023.00379.
  22. Open and Closed World Assumptions in Data Exchange. Description Logics, 477, 2009.
  23. Neural-Answering Logical Queries on Knowledge Graphs. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp.  1087–1097, 2021.
  24. Liu, T.-Y. et al. Learning to rank for information retrieval. Foundations and Trends® in Information Retrieval, 3(3):225–331, 2009.
  25. Logic embeddings for complex query answering. arXiv preprint arXiv:2103.00418, 2021.
  26. Marker, D. Model theory: an introduction, volume 217. Springer Science & Business Media, 2006.
  27. Miller, G. A. WordNet: A lexical database for English. Communications of the ACM, 38(11):39–41, November 1995. ISSN 0001-0782. doi: 10.1145/219717.219748.
  28. Learning embeddings from knowledge graphs with numeric edge attributes. arXiv preprint arXiv:2105.08683, 2021.
  29. A language modeling approach to information retrieval. In ACM SIGIR Forum, volume 51, pp.  202–208. ACM New York, NY, USA, 2017.
  30. Beta embeddings for multi-hop logical reasoning in knowledge graphs. Advances in Neural Information Processing Systems, 33:19716–19726, 2020.
  31. Query2box: Reasoning Over Knowledge Graphs In Vector Space Using Box Embeddings. In International Conference on Learning Representations (ICLR), 2020.
  32. Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases, March 2023. URL http://arxiv.org/abs/2303.14617. arXiv:2303.14617 [cs].
  33. Exact and inexact graph matching: Methodology and applications. Managing and mining graph data, pp.  217–247, 2010.
  34. Handbook of Constraint Programming. Elsevier Science Inc., USA, 2006. ISBN 978-0-08-046380-3.
  35. Schiex, T. Possibilistic constraint satisfaction problems or “how to handle soft constraints?”. In Uncertainty in Artificial Intelligence, pp.  268–275. Elsevier, 1992.
  36. Conceptnet 5.5: An open multilingual graph of general knowledge. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, pp.  4444–4451. AAAI Press, 2017.
  37. Yago: a core of semantic knowledge. In Proceedings of the 16th international conference on World Wide Web, pp.  697–706, 2007.
  38. Probabilistic databases. Springer Nature, 2022.
  39. The string database in 2023: protein–protein association networks and functional enrichment analyses for any sequenced genome of interest. Nucleic acids research, 51(D1):D638–D646, 2023.
  40. Complex embeddings for simple link prediction. In International conference on machine learning, pp.  2071–2080. PMLR, 2016.
  41. Attention is all you need. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (eds.), Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017.
  42. Wikidata: a free collaborative knowledgebase. Communications of the ACM, 57(10):78–85, 2014. Publisher: ACM New York, NY, USA.
  43. Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, 1, December 2021.
  44. Logical Queries on Knowledge Graphs: Emerging Interface of Incomplete Relational Data. Data Engineering, pp.  3, 2022.
  45. Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport. arXiv preprint arXiv:2305.04034, 2023a.
  46. Logical Message Passing Networks with One-hop Inference on Atomic Formulas. In The Eleventh International Conference on Learning Representations, 2023b. URL https://openreview.net/forum?id=SoyOsp7i_l.
  47. Embedding entities and relations for learning and inference in knowledge bases. In Bengio, Y. and LeCun, Y. (eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015. URL http://arxiv.org/abs/1412.6575.
  48. GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphs, October 2022. URL http://arxiv.org/abs/2210.15578. arXiv:2210.15578 [cs].
  49. EFOksubscriptEFO𝑘\text{EFO}_{k}EFO start_POSTSUBSCRIPT italic_k end_POSTSUBSCRIPT-CQA: Towards knowledge graph complex query answering beyond set operation. arXiv preprint arXiv:2307.13701, 2023.
  50. Rethinking existential first order queries and their inference on knowledge graphs. In The Twelfth International Conference on Learning Representations, 2024.
  51. Aser: A large-scale eventuality knowledge graph. In Proceedings of the web conference 2020, pp.  201–211, 2020.
  52. Cone: Cone embeddings for multi-hop reasoning over knowledge graphs. Advances in Neural Information Processing Systems, 34:19172–19183, 2021.
  53. Neural-Symbolic Models for Logical Queries on Knowledge Graphs. arXiv preprint arXiv:2205.10128, 2022.
Citations (4)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up