Papers
Topics
Authors
Recent
Search
2000 character limit reached

Relational Graph Convolutional Networks Do Not Learn Sound Rules

Published 14 Aug 2024 in cs.LG, cs.AI, and cs.LO | (2408.10261v1)

Abstract: Graph neural networks (GNNs) are frequently used to predict missing facts in knowledge graphs (KGs). Motivated by the lack of explainability for the outputs of these models, recent work has aimed to explain their predictions using Datalog, a widely used logic-based formalism. However, such work has been restricted to certain subclasses of GNNs. In this paper, we consider one of the most popular GNN architectures for KGs, R-GCN, and we provide two methods to extract rules that explain its predictions and are sound, in the sense that each fact derived by the rules is also predicted by the GNN, for any input dataset. Furthermore, we provide a method that can verify that certain classes of Datalog rules are not sound for the R-GCN. In our experiments, we train R-GCNs on KG completion benchmarks, and we are able to verify that no Datalog rule is sound for these models, even though the models often obtain high to near-perfect accuracy. This raises some concerns about the ability of R-GCN models to generalise and about the explainability of their predictions. We further provide two variations to the training paradigm of R-GCN that encourage it to learn sound rules and find a trade-off between model accuracy and the number of learned sound rules.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. 2020. Boxe: A box embedding model for knowledge base completion. In Larochelle, H.; Ranzato, M.; Hadsell, R.; Balcan, M.; and Lin, H., eds., Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
  2. 2013. Translating embeddings for modeling multi-relational data. Advances in neural information processing systems 26.
  3. 2015. On approximate reasoning capabilities of low-rank vector spaces. In 2015 AAAI Spring Symposium Series.
  4. 2019. Transgcn: Coupling transformation assumptions with graph convolutional networks for link prediction. In Proceedings of the 10th international conference on knowledge capture, 131–138.
  5. 2018. Convolutional 2d knowledge graph embeddings. In Proceedings of the AAAI conference on artificial intelligence, volume 32.
  6. 2018. Learning explanatory rules from noisy data. Journal of Artificial Intelligence Research 61:1–64.
  7. 2019. Reconciling deep learning with symbolic artificial intelligence: representing objects and relations. Current Opinion in Behavioral Sciences 29:17–23.
  8. 2023. Drew: Dynamically rewired message passing with delay. In International Conference on Machine Learning, 12252–12267. PMLR.
  9. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems 30.
  10. 2022. Knowledge graphs. ACM Comput. Surv. 54(4):71:1–71:37.
  11. 2019. A recurrent graph neural network for multi-relational data. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 8157–8161. IEEE.
  12. 2023. Skier: A symbolic knowledge integrated model for conversational emotion recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, 13121–13129.
  13. 2023. Fusing topology contexts and logical rules in language models for knowledge graph completion. Information Fusion 90:253–264.
  14. 2021. Indigo: Gnn-based inductive knowledge graph completion using pair-wise encoding. Advances in Neural Information Processing Systems 34:2034–2045.
  15. 2023. Revisiting inferential benchmarks for knowledge graph completion. In Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning, volume 19, 461–471.
  16. 2018. Fine-grained evaluation of rule-and embedding-based systems for knowledge graph completion. In The Semantic Web–ISWC 2018: 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018, Proceedings, Part I 17, 3–20. Springer.
  17. 2011. A three-way model for collective learning on multi-relational data. In Icml, volume 11, 3104482–3104584.
  18. 2022. Gnnq: A neuro-symbolic approach to query answering over incomplete knowledge graphs. In International Semantic Web Conference, 481–497. Springer.
  19. 2020. Rnnlogic: Learning logic rules for reasoning on knowledge graphs. In International Conference on Learning Representations.
  20. 2017. End-to-end differentiable proving. Advances in neural information processing systems 30.
  21. 2019. Drum: End-to-end differentiable rule mining on knowledge graphs. Advances in Neural Information Processing Systems 32.
  22. 2018. Modeling relational data with graph convolutional networks. In The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3–7, 2018, Proceedings 15, 593–607. Springer.
  23. 2019. End-to-end structure-aware convolutional networks for knowledge base completion. In Proceedings of the AAAI conference on artificial intelligence, volume 33, 3060–3067.
  24. 2007. Yago: a core of semantic knowledge. In Proceedings of the 16th international conference on World Wide Web, 697–706.
  25. 2018. Rotate: Knowledge graph embedding by relational rotation in complex space. In International Conference on Learning Representations.
  26. 2024. Gadbench: Revisiting and benchmarking supervised graph anomaly detection. Advances in Neural Information Processing Systems 36.
  27. 2021. Explainable gnn-based models over knowledge graphs. In International Conference on Learning Representations.
  28. 2023. On the Correspondence Between Monotonic Max-Sum GNNs and Datalog. In Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning, 658–667.
  29. 2022. Faithful approaches to rule learning. In Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning, volume 19, 484–493.
  30. 2020. Inductive relation prediction by subgraph reasoning. In International Conference on Machine Learning, 9448–9457. PMLR.
  31. 2020. Ra-gcn: Relational aggregation graph convolutional network for knowledge graph completion. In Proceedings of the 2020 12th international conference on machine learning and computing, 580–586.
  32. 2015. Observed versus latent features for knowledge base and text inference. In Proceedings of the 3rd workshop on continuous vector space models and their compositionality, 57–66.
  33. 2019. Composition-based multi-relational graph convolutional networks. In International Conference on Learning Representations.
  34. 2014. Wikidata: a free collaborative knowledgebase. Communications of the ACM 57(10):78–85.
  35. 2023. Faithful rule extraction for differentiable rule learning models. In The Twelfth International Conference on Learning Representations.
  36. 2022. From discrimination to generation: Knowledge graph completion with generative transformer. In Companion Proceedings of the Web Conference 2022, 162–165.
  37. 2015. Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of the International Conference on Learning Representations (ICLR) 2015.
  38. 2017. Differentiable learning of logical rules for knowledge base reasoning. Advances in neural information processing systems 30.
  39. 2019. Kg-bert: Bert for knowledge graph completion. arXiv preprint arXiv:1909.03193.
  40. 2021. Knowledge embedding based graph convolutional network. In Proceedings of the Web Conference 2021, 1619–1628.
  41. 2023. Learning latent relations for temporal knowledge graph reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 12617–12631.

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

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free