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

One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion (2404.15807v1)

Published 24 Apr 2024 in cs.CL

Abstract: Knowledge Graph Completion (KGC) has garnered massive research interest recently, and most existing methods are designed following a transductive setting where all entities are observed during training. Despite the great progress on the transductive KGC, these methods struggle to conduct reasoning on emerging KGs involving unseen entities. Thus, inductive KGC, which aims to deduce missing links among unseen entities, has become a new trend. Many existing studies transform inductive KGC as a graph classification problem by extracting enclosing subgraphs surrounding each candidate triple. Unfortunately, they still face certain challenges, such as the expensive time consumption caused by the repeat extraction of enclosing subgraphs, and the deficiency of entity-independent feature learning. To address these issues, we propose a global-local anchor representation (GLAR) learning method for inductive KGC. Unlike previous methods that utilize enclosing subgraphs, we extract a shared opening subgraph for all candidates and perform reasoning on it, enabling the model to perform reasoning more efficiently. Moreover, we design some transferable global and local anchors to learn rich entity-independent features for emerging entities. Finally, a global-local graph reasoning model is applied on the opening subgraph to rank all candidates. Extensive experiments show that our GLAR outperforms most existing state-of-the-art methods.

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 (62)
  1. F. M. Suchanek, G. Kasneci, and G. Weikum, “Yago: a core of semantic knowledge,” in Proceedings of the 16th International Conference on World Wide Web, 2007, pp. 697–706.
  2. K. D. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor, “Freebase: a collaboratively created graph database for structuring human knowledge,” in Proceedings of the ACM SIGMOD International Conference on Management of Data, 2008, pp. 1247–1250.
  3. J. Lehmann, R. Isele, M. Jakob, A. Jentzsch, D. Kontokostas, P. N. Mendes, S. Hellmann, M. Morsey, P. van Kleef, S. Auer, and C. Bizer, “Dbpedia - A large-scale, multilingual knowledge base extracted from wikipedia,” Semantic Web, vol. 6, no. 2, pp. 167–195, 2015.
  4. D. Vrandecic and M. Krötzsch, “Wikidata: a free collaborative knowledgebase,” Commun. ACM, vol. 57, no. 10, pp. 78–85, 2014.
  5. C. Xiong, R. Power, and J. Callan, “Explicit semantic ranking for academic search via knowledge graph embedding,” in Proceedings of the 26th International Conference on World Wide Web, 2017, pp. 1271–1279.
  6. N. Zhang, Q. Jia, S. Deng, X. Chen, H. Ye, H. Chen, H. Tou, G. Huang, Z. Wang, N. Hua, and H. Chen, “AliCG: Fine-grained and evolvable conceptual graph construction for semantic search at alibaba,” in KDD ’21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, 2021, pp. 3895–3905.
  7. M. Yasunaga, H. Ren, A. Bosselut, P. Liang, and J. Leskovec, “QA-GNN: reasoning with language models and knowledge graphs for question answering,” in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 535–546.
  8. J. Li and D. Xiong, “Kafsp: Knowledge-aware fuzzy semantic parsing for conversational question answering over a large-scale knowledge base,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 461–473.
  9. F. Wan, W. Shen, K. Yang, X. Quan, and W. Bi, “Multi-grained knowledge retrieval for end-to-end task-oriented dialog,” in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, pp. 11 196–11 210.
  10. M. R. A. H. Rony, R. Usbeck, and J. Lehmann, “Dialokg: Knowledge-structure aware task-oriented dialogue generation,” in Findings of the Association for Computational Linguistics: NAACL 2022, 2022, pp. 2557–2571.
  11. K. K. Teru, E. G. Denis, and W. L. Hamilton, “Inductive relation prediction by subgraph reasoning,” in Proceedings of the 37th International Conference on Machine Learning, vol. 119, 2020, pp. 9448–9457.
  12. S. Mai, S. Zheng, Y. Yang, and H. Hu, “Communicative message passing for inductive relation reasoning,” in Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021, pp. 4294–4302.
  13. J. Chen, H. He, F. Wu, and J. Wang, “Topology-aware correlations between relations for inductive link prediction in knowledge graphs,” in Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021, pp. 6271–6278.
  14. Q. Lin, J. Liu, F. Xu, Y. Pan, Y. Zhu, L. Zhang, and T. Zhao, “Incorporating context graph with logical reasoning for inductive relation prediction,” in SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2022, pp. 893–903.
  15. A. Bordes, N. Usunier, A. García-Durán, J. Weston, and O. Yakhnenko, “Translating embeddings for modeling multi-relational data,” in Advances in Neural Information Processing Systems, 2013, pp. 2787–2795.
  16. Z. Sun, Z. Deng, J. Nie, and J. Tang, “RotatE: Knowledge graph embedding by relational rotation in complex space,” in 7th International Conference on Learning Representations, 2019.
  17. S. Vashishth, S. Sanyal, V. Nitin, and P. P. Talukdar, “Composition-based multi-relational graph convolutional networks,” in 8th International Conference on Learning Representations, 2020.
  18. M. S. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, and M. Welling, “Modeling relational data with graph convolutional networks,” in The Semantic Web - 15th International Conference, 2018, pp. 593–607.
  19. Y. Zhang, Z. Zhou, Q. Yao, and Y. Li, “KGTuner: Efficient hyper-parameter search for knowledge graph embedding,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 2715–2735.
  20. Z. Xie, G. Zhou, J. Liu, and J. X. Huang, “ReInceptionE: Relation-aware inception network with joint local-global structural information for knowledge graph embedding,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 5929–5939.
  21. L. Chao, J. He, T. Wang, and W. Chu, “PairRE: Knowledge graph embeddings via paired relation vectors,” in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021, pp. 4360–4369.
  22. C. Meilicke, M. Fink, Y. Wang, D. Ruffinelli, R. Gemulla, and H. Stuckenschmidt, “Fine-grained evaluation of rule- and embedding-based systems for knowledge graph completion,” in The Semantic Web - ISWC 2018 - 17th International Semantic Web Conference, vol. 11136, 2018, pp. 3–20.
  23. A. Sadeghian, M. Armandpour, P. Ding, and D. Z. Wang, “DRUM: end-to-end differentiable rule mining on knowledge graphs,” in Advances in Neural Information Processing Systems, 2019, pp. 15 321–15 331.
  24. F. Yang, Z. Yang, and W. W. Cohen, “Differentiable learning of logical rules for knowledge base reasoning,” in Advances in Neural Information Processing Systems, 2017, pp. 2319–2328.
  25. S. Zheng, S. Mai, Y. Sun, H. Hu, and Y. Yang, “Subgraph-aware few-shot inductive link prediction via meta-learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 6, pp. 6512–6517, 2023.
  26. Z. Xie, Y. Zhang, J. Liu, G. Zhou, and J. X. Huang, “Learning query adaptive anchor representation for inductive relation prediction,” in Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 14 041–14 053.
  27. Z. Wang, J. Zhang, J. Feng, and Z. Chen, “Knowledge graph embedding by translating on hyperplanes,” in Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014, pp. 1112–1119.
  28. Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu, “Learning entity and relation embeddings for knowledge graph completion,” in Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015, pp. 2181–2187.
  29. Z. Zhang, J. Cai, Y. Zhang, and J. Wang, “Learning hierarchy-aware knowledge graph embeddings for link prediction,” in The Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 3065–3072.
  30. M. Nickel, V. Tresp, and H. Kriegel, “A three-way model for collective learning on multi-relational data,” in Proceedings of the 28th International Conference on Machine Learning, 2011, pp. 809–816.
  31. B. Yang, W. Yih, X. He, J. Gao, and L. Deng, “Embedding entities and relations for learning and inference in knowledge bases,” in 3rd International Conference on Learning Representations, 2015.
  32. T. Trouillon, J. Welbl, S. Riedel, É. Gaussier, and G. Bouchard, “Complex embeddings for simple link prediction,” in Proceedings of the 33nd International Conference on Machine Learning, 2016, pp. 2071–2080.
  33. T. Dettmers, P. Minervini, P. Stenetorp, and S. Riedel, “Convolutional 2D knowledge graph embeddings,” in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018, pp. 1811–1818.
  34. X. Jiang, Q. Wang, and B. Wang, “Adative convolution for multi-relational learning,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, 2019, pp. 978–987.
  35. S. Vashishth, S. Sanyal, V. Nitin, N. Agrawal, and P. P. Talukdar, “Interacte: Improving convolution-based knowledge graph embeddings by increasing feature interactions,” in The Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020, pp. 3009–3016.
  36. J. Wu, W. Shi, X. Cao, J. Chen, W. Lei, F. Zhang, W. Wu, and X. He, “DisenKGAT: Knowledge graph embedding with disentangled graph attention network,” in Proceedings of the 30th ACM International Conference on Information and Knowledge Management, 2021, pp. 2140–2149.
  37. H. Lee, J. Im, S. Jang, H. Cho, and S. Chung, “Melu: Meta-learned user preference estimator for cold-start recommendation,” in Proceedings of the 25th ACM SIGKDD International Conference onKnowledge Discovery & Data Mining, 2019, pp. 1073–1082.
  38. Q. Wu, H. Zhang, X. Gao, J. Yan, and H. Zha, “Towards open-world recommendation: An inductive model-based collaborative filtering approach,” in Proceedings of the 38th International Conference on Machine Learning, vol. 139, 2021, pp. 11 329–11 339.
  39. T. Qian, Y. Liang, and Q. Li, “Solving cold start problem in recommendation with attribute graph neural networks,” CoRR, vol. abs/1912.12398, 2019.
  40. K. Zhong, Z. Song, P. Jain, and I. S. Dhillon, “Nonlinear inductive matrix completion based on one-layer neural networks,” CoRR, vol. abs/1805.10477, 2018.
  41. Y. Zhang, W. Wang, H. Yin, P. Zhao, W. Chen, and L. Zhao, “Disconnected emerging knowledge graph oriented inductive link prediction,” in 39th IEEE International Conference on Data Engineering, 2023, pp. 381–393.
  42. L. Yao, C. Mao, and Y. Luo, “KG-BERT: BERT for knowledge graph completion,” CoRR, vol. abs/1909.03193, 2019.
  43. J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019, pp. 4171–4186.
  44. X. Wang, T. Gao, Z. Zhu, Z. Zhang, Z. Liu, J. Li, and J. Tang, “KEPLER: A unified model for knowledge embedding and pre-trained language representation,” Trans. Assoc. Comput. Linguistics, vol. 9, pp. 176–194, 2021.
  45. H. Zha, Z. Chen, and X. Yan, “Inductive relation prediction by BERT,” in Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022, pp. 5923–5931.
  46. L. Wang, W. Zhao, Z. Wei, and J. Liu, “Simkgc: Simple contrastive knowledge graph completion with pre-trained language models,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 4281–4294.
  47. M. Chen, W. Zhang, Y. Zhu, H. Zhou, Z. Yuan, C. Xu, and H. Chen, “Meta-knowledge transfer for inductive knowledge graph embedding,” in SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2022, pp. 927–937.
  48. M. Galkin, E. G. Denis, J. Wu, and W. L. Hamilton, “Nodepiece: Compositional and parameter-efficient representations of large knowledge graphs,” in The Tenth International Conference on Learning Representations, 2022.
  49. Q. Li, S. Joty, D. Wang, S. Feng, Y. Zhang, and C. Qin, “Contrastive learning with generated representations for inductive knowledge graph embedding,” in Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 14 273–14 287.
  50. X. Li, B. Ning, G. Li, and W. Jie, “Relation-attention semantic-correlative knowledge graph embedding for inductive link prediction,” Int. J. Mach. Learn. Cybern., vol. 14, no. 11, pp. 3799–3811, 2023.
  51. H. A. Mohamed, D. Pilutti, S. James, A. D. Bue, M. Pelillo, and S. Vascon, “Locality-aware subgraphs for inductive link prediction in knowledge graphs,” Pattern Recognit. Lett., vol. 167, pp. 90–97, 2023.
  52. X. Xu, P. Zhang, Y. He, C. Chao, and C. Yan, “Subgraph neighboring relations infomax for inductive link prediction on knowledge graphs,” in Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022, pp. 2341–2347.
  53. K. Sun, H. Jiang, Y. Hu, and B. Yin, “Substructure-aware subgraph reasoning for inductive relation prediction,” J. Supercomput., vol. 79, no. 18, pp. 21 008–21 027, 2023.
  54. J. Lee, C. Chung, and J. J. Whang, “Ingram: Inductive knowledge graph embedding via relation graphs,” in International Conference on Machine Learning, vol. 202, 2023, pp. 18 796–18 809.
  55. Y. Geng, J. Chen, J. Z. Pan, M. Chen, S. Jiang, W. Zhang, and H. Chen, “Relational message passing for fully inductive knowledge graph completion,” in 39th IEEE International Conference on Data Engineering, 2023, pp. 1221–1233.
  56. G. A. Gesese, H. Sack, and M. Alam, “RAILD: towards leveraging relation features for inductive link prediction in knowledge graphs,” in Proceedings of the 11th International Joint Conference on Knowledge Graphs, 2022, pp. 82–90.
  57. K. Toutanova, D. Chen, P. Pantel, H. Poon, P. Choudhury, and M. Gamon, “Representing text for joint embedding of text and knowledge bases,” in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, pp. 1499–1509.
  58. W. Xiong, T. Hoang, and W. Y. Wang, “Deeppath: A reinforcement learning method for knowledge graph reasoning,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 564–573.
  59. M. Wang, L. Yu, D. Zheng, Q. Gan, Y. Gai, Z. Ye, M. Li, J. Zhou, Q. Huang, C. Ma, Z. Huang, Q. Guo, H. Zhang, H. Lin, J. Zhao, J. Li, A. J. Smola, and Z. Zhang, “Deep graph library: Towards efficient and scalable deep learning on graphs,” CoRR, vol. abs/1909.01315, 2019.
  60. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in 3rd International Conference on Learning Representations, 2015.
  61. Z. Zhu, Z. Zhang, L.-P. A. C. Xhonneux, and J. Tang, “Neural bellman-ford networks: A general graph neural network framework for link prediction,” in Advances in Neural Information Processing Systems, 2021, pp. 29 476–29 490.
  62. T. Liu, Q. Lv, J. Wang, S. Yang, and H. Chen, “Learning rule-induced subgraph representations for inductive relation prediction,” in Advances in Neural Information Processing Systems, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Zhiwen Xie (8 papers)
  2. Yi Zhang (994 papers)
  3. Guangyou Zhou (4 papers)
  4. Jin Liu (151 papers)
  5. Xinhui Tu (3 papers)
  6. Jimmy Xiangji Huang (18 papers)