Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation (2312.15643v3)

Published 25 Dec 2023 in cs.AI and cs.CL

Abstract: Abductive reasoning is the process of making educated guesses to provide explanations for observations. Although many applications require the use of knowledge for explanations, the utilization of abductive reasoning in conjunction with structured knowledge, such as a knowledge graph, remains largely unexplored. To fill this gap, this paper introduces the task of complex logical hypothesis generation, as an initial step towards abductive logical reasoning with KG. In this task, we aim to generate a complex logical hypothesis so that it can explain a set of observations. We find that the supervised trained generative model can generate logical hypotheses that are structurally closer to the reference hypothesis. However, when generalized to unseen observations, this training objective does not guarantee better hypothesis generation. To address this, we introduce the Reinforcement Learning from Knowledge Graph (RLF-KG) method, which minimizes differences between observations and conclusions drawn from generated hypotheses according to the KG. Experiments show that, with RLF-KG's assistance, the generated hypotheses provide better explanations, and achieve state-of-the-art results on three widely used KGs.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Neural methods for logical reasoning over knowledge graphs. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, 2022. URL https://openreview.net/forum?id=tgcAoUVHRIB.
  2. Query2Particles: Knowledge graph reasoning with particle embeddings. In Findings of the Association for Computational Linguistics: NAACL 2022, pp.  2703–2714, Seattle, United States, July 2022. Association for Computational Linguistics. doi: 10.18653/v1/2022.findings-naacl.207. URL https://aclanthology.org/2022.findings-naacl.207.
  3. Sequential query encoding for complex query answering on knowledge graphs. Transactions on Machine Learning Research, 2023. ISSN 2835-8856. URL https://openreview.net/forum?id=ERqGqZzSu5.
  4. Freebase: a collaboratively created graph database for structuring human knowledge. In Jason Tsong-Li Wang (ed.), Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, Vancouver, BC, Canada, June 10-12, 2008, pp.  1247–1250. ACM, 2008. doi: 10.1145/1376616.1376746. URL https://doi.org/10.1145/1376616.1376746.
  5. Smatch: an evaluation metric for semantic feature structures. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, 4-9 August 2013, Sofia, Bulgaria, Volume 2: Short Papers, pp.  748–752. The Association for Computer Linguistics, 2013. URL https://aclanthology.org/P13-2131/.
  6. Abductive reasoning in cognitive neuroscience: Weak and strong reverse inference. Synthese, 200(2):1–26, 2022. doi: 10.1007/s11229-022-03585-2.
  7. Fuzzy logic based logical query answering on knowledge graphs. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pp.  3939–3948. AAAI Press, 2022. URL https://ojs.aaai.org/index.php/AAAI/article/view/20310.
  8. Rlogic: Recursive logical rule learning from knowledge graphs. In Aidong Zhang and Huzefa Rangwala (eds.), KDD ’22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14 - 18, 2022, pp.  179–189. ACM, 2022. doi: 10.1145/3534678.3539421. URL https://doi.org/10.1145/3534678.3539421.
  9. Neural compositional rule learning for knowledge graph reasoning. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. URL https://openreview.net/pdf?id=F8VKQyDgRVj.
  10. Probabilistic entity representation model for reasoning over knowledge graphs. In Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (eds.), Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 23440–23451, 2021a. URL https://proceedings.neurips.cc/paper/2021/hash/c4d2ce3f3ebb5393a77c33c0cd95dc93-Abstract.html.
  11. Self-supervised hyperboloid representations from logical queries over knowledge graphs. In Jure Leskovec, Marko Grobelnik, Marc Najork, Jie Tang, and Leila Zia (eds.), WWW ’21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021, pp.  1373–1384. ACM / IW3C2, 2021b. doi: 10.1145/3442381.3449974. URL https://doi.org/10.1145/3442381.3449974.
  12. Bridging machine learning and logical reasoning by abductive learning. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pp.  2811–2822, 2019. URL https://proceedings.neurips.cc/paper/2019/hash/9c19a2aa1d84e04b0bd4bc888792bd1e-Abstract.html.
  13. The open world assumption. In eSI Workshop: The Closed World of Databases meets the Open World of the Semantic Web, volume 15, pp.  1, 2006.
  14. Fast rule mining in ontological knowledge bases with AMIE+. VLDB J., 24(6):707–730, 2015. doi: 10.1007/s00778-015-0394-1. URL https://doi.org/10.1007/s00778-015-0394-1.
  15. Brian D. Haig. Abductive Learning, pp.  10–12. Springer US, Boston, MA, 2012. ISBN 978-1-4419-1428-6. doi: 10.1007/978-1-4419-1428-6˙830. URL https://doi.org/10.1007/978-1-4419-1428-6_830.
  16. Embedding logical queries on knowledge graphs. In Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pp.  2030–2041, 2018. URL https://proceedings.neurips.cc/paper/2018/hash/ef50c335cca9f340bde656363ebd02fd-Abstract.html.
  17. Rule learning from knowledge graphs guided by embedding models. In Denny Vrandecic, Kalina Bontcheva, Mari Carmen Suárez-Figueroa, Valentina Presutti, Irene Celino, Marta Sabou, Lucie-Aimée Kaffee, and Elena Simperl (eds.), The Semantic Web - ISWC 2018 - 17th International Semantic Web Conference, Monterey, CA, USA, October 8-12, 2018, Proceedings, Part I, volume 11136 of Lecture Notes in Computer Science, pp.  72–90. Springer, 2018. doi: 10.1007/978-3-030-00671-6_5. URL https://doi.org/10.1007/978-3-030-00671-6_5.
  18. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans. Neural Networks Learn. Syst., 33(2):494–514, 2022. doi: 10.1109/TNNLS.2021.3070843. URL https://doi.org/10.1109/TNNLS.2021.3070843.
  19. Abductive inference: Computation, philosophy, technology. Cambridge University Press, 1996.
  20. Neural-answering logical queries on knowledge graphs. In Feida Zhu, Beng Chin Ooi, and Chunyan Miao (eds.), KDD ’21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, Singapore, August 14-18, 2021, pp.  1087–1097. ACM, 2021. doi: 10.1145/3447548.3467375. URL https://doi.org/10.1145/3447548.3467375.
  21. Lorenzo Magnani. Handbook of Abductive Cognition. Springer International Publishing, 2023. ISBN 9783031101359. URL https://books.google.com.hk/books?id=6yC3EAAAQBAJ.
  22. Carlo Martini. Abductive Reasoning in Clinical Diagnostics, pp.  467–479. Springer International Publishing, Cham, 2023. ISBN 978-3-031-10135-9. doi: 10.1007/978-3-031-10135-9˙13. URL https://doi.org/10.1007/978-3-031-10135-9_13.
  23. Anytime bottom-up rule learning for knowledge graph completion. In Sarit Kraus (ed.), Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, August 10-16, 2019, pp.  3137–3143. ijcai.org, 2019. doi: 10.24963/ijcai.2019/435. URL https://doi.org/10.24963/ijcai.2019/435.
  24. Training language models to follow instructions with human feedback. In NeurIPS, 2022. URL http://papers.nips.cc/paper_files/paper/2022/hash/b1efde53be364a73914f58805a001731-Abstract-Conference.html.
  25. Beta embeddings for multi-hop logical reasoning in knowledge graphs. In Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020. URL https://proceedings.neurips.cc/paper/2020/hash/e43739bba7cdb577e9e3e4e42447f5a5-Abstract.html.
  26. Query2box: Reasoning over knowledge graphs in vector space using box embeddings. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. URL https://openreview.net/forum?id=BJgr4kSFDS.
  27. Proximal Policy Optimization Algorithms, August 2017. URL http://arxiv.org/abs/1707.06347. arXiv:1707.06347 [cs].
  28. Open-world knowledge graph completion. In Sheila A. McIlraith and Kilian Q. Weinberger (eds.), Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, pp.  1957–1964. AAAI Press, 2018. doi: 10.1609/aaai.v32i1.11535. URL https://doi.org/10.1609/aaai.v32i1.11535.
  29. Faithful embeddings for knowledge base queries. In Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020. URL https://proceedings.neurips.cc/paper/2020/hash/fe74074593f21197b7b7be3c08678616-Abstract.html.
  30. Abductive reasoning: Logic, visual thinking, and coherence. In Logic and Scientific Methods: Volume One of the Tenth International Congress of Logic, Methodology and Philosophy of Science, Florence, August 1995, pp.  413–427. Springer, 1997.
  31. Observed versus latent features for knowledge base and text inference. In Alexandre Allauzen, Edward Grefenstette, Karl Moritz Hermann, Hugo Larochelle, and Scott Wen-tau Yih (eds.), Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, CVSC 2015, Beijing, China, July 26-31, 2015, pp.  57–66. Association for Computational Linguistics, 2015. doi: 10.18653/v1/W15-4007. URL https://doi.org/10.18653/v1/W15-4007.
  32. Attention is all you need. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp.  5998–6008, 2017. URL https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html.
  33. Gammae: Gamma embeddings for logical queries on knowledge graphs. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (eds.), Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pp.  745–760. Association for Computational Linguistics, 2022. URL https://aclanthology.org/2022.emnlp-main.47.
  34. Neural, symbolic and neural-symbolic reasoning on knowledge graphs. AI Open, 2:14–35, 2021a. doi: 10.1016/j.aiopen.2021.03.001. URL https://doi.org/10.1016/j.aiopen.2021.03.001.
  35. Knowledge graph reasoning with logics and embeddings: Survey and perspective. CoRR, abs/2202.07412, 2022. URL https://arxiv.org/abs/2202.07412.
  36. Cone: Cone embeddings for multi-hop reasoning over knowledge graphs. In Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (eds.), Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 19172–19183, 2021b. URL https://proceedings.neurips.cc/paper/2021/hash/a0160709701140704575d499c997b6ca-Abstract.html.
  37. Fine-Tuning Language Models from Human Preferences, January 2020. URL http://arxiv.org/abs/1909.08593. arXiv:1909.08593 [cs, stat].
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Jiaxin Bai (30 papers)
  2. Yicheng Wang (41 papers)
  3. Tianshi Zheng (19 papers)
  4. Yue Guo (29 papers)
  5. Xin Liu (820 papers)
  6. Yangqiu Song (196 papers)
Citations (1)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets