Abstract
In this paper, we introduce our solution for the inductive knowledge graph reasoning task organized by the 2023 China Conference on Knowledge Graph and Semantic Computing (CCKS 2023). Specifically, this inductive knowledge graph reasoning task has two main challenges, namely 1) How to predict the entities that are not in the training set, and 2) How to train and reason more efficiently. To deal with these challenges, we adapt the Neural Bellman-Ford Networks (NBFNet) with grid search strategy for achieving the best performance. Along this line, we further refine this solution with ensemble learning and post-processing. Extensive experiments have demonstrated the effectiveness of our solution, which won the first place in the competition. Code is publicly available at https://github.com/smart-lty/CCKS-2023-Task2
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhang, Z., et al.: ERNIE: enhanced language representation with informative entities. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, July 2019, pp. 1441–1451. Association for Computational Linguistics. https://doi.org/10.18653/v1/P19-1139. https://aclanthology.org/P19-1139
Wang, H., et al.: RippleNet: propagating user preferences on the knowledge graph for recommender systems. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, CIKM 2018, Torino, Italy, pp. 417–426. Association for Computing Machinery (2018). ISBN 9781450360142. https://doi.org/10.1145/3269206.3271739
Huang, X., et al.: Knowledge graph embedding based question answering. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, WSDM 2019, Melbourne, VIC, Australia, pp. 105–113. Association for Computing Machinery (2019). ISBN 9781450359405. https://doi.org/10.1145/3289600.3290956
Bollacker, K., et al.: Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, Vancouver, Canada, pp. 1247–1250. Association for Computing Machinery (2008). ISBN 9781605581026. https://doi.org/10.1145/1376616.1376746
Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78–85 (2014). ISSN 0001-0782. https://doi.org/10.1145/2629489
Mahdisoltani, F., Biega, J.A., Suchanek, F.M.: YAGO3: a knowledge base from multilingual Wikipedias. In: Conference on Innovative Data Systems Research (2015). https://api.semanticscholar.org/CorpusID:6611164
Sun, Z., et al.: RotatE: knowledge graph embedding by relational rotation in complex space. arXiv:1902.10197 [cs.LG] (2019)
Schlichtkrull, M., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 593–607. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93417-4_38
Galkin, M., Berrendorf, M., Hoyt, C.T.: An open challenge for inductive link prediction on knowledge graphs (2022)
Teru, K.K., Denis, E.G., Hamilton, W.L.: Inductive relation prediction by subgraph reasoning. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020. JMLR.org (2020)
Chen, J., et al.: Topology-aware correlations between relations for inductive link prediction in knowledge graphs. Proc. AAAI Conf. Artif. Intell. 35(7), 6271–6278 (2021). https://doi.org/10.1609/aaai.v35i7.16779. https://ojs.aaai.org/index.php/AAAI/article/view/16779.
Galárraga, L., et al.: Fast rule mining in ontological knowledge bases with AMIE+. VLDB J. 24(6), 707–730 (2015). ISSN 1066-8888. https://doi.org/10.1007/s00778-015-0394-1
Yang, F., Yang, Z., Cohen, W.W.: Differentiable learning of logical rules for knowledge base reasoning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, Long Beach, California, USA, pp. 2316–2325. Curran Associates Inc. (2017). ISBN 9781510860964
Kok, S., Domingos, P.: Statistical predicate invention. In: Proceedings of the 24th International Conference on Machine Learning, ICML 2007, Corvalis, Oregon, USA, pp. 433–440. Association for Computing Machinery (2007). ISBN 9781595937933. https://doi.org/10.1145/1273496.1273551
Wang, W.Y., Mazaitis, K., Cohen, W.W.: Structure learning via parameter learning. In: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, CIKM 2014, Shanghai, China, pp. 1199–1208. Association for Computing Machinery (2014). ISBN 9781450325981. https://doi.org/10.1145/2661829.2662022
Mai, S., et al.: Communicative message passing for inductive relation reasoning. arXiv:2012.08911 [cs.AI] (2021)
Rameshkumar, K., Sambath, M., Ravi, S.: Relevant association rule mining from medical dataset using new irrelevant rule elimination technique. In: 2013 International Conference on Information Communication and Embedded Systems (ICICES), ICICES 2013, pp. 300–304 (2013). https://doi.org/10.1109/ICICES.2013.6508351
Katz, L.: A new status index derived from sociometric analysis. Psychometrika 18(1), 39–43 (1953)
Brin, S.: The PageRank citation ranking: bringing order to the web. In: Proceedings of ASIS 1998, vol. 98, pp. 161–172 (1998)
Liben-Nowell, D., Kleinberg, J.: The link prediction problem for social networks. In: Proceedings of the Twelfth International Conference on Information and Knowledge Management, pp. 556–559 (2003)
Baras, J., Theodorakopoulos, G.: Path Problems in Networks. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-79983-9
Bellman, R.: On a routing problem. Q. Appl. Math. 16(1), 87–90 (1958)
Galárraga, L.A., et al.: AMIE: association rule mining under incomplete evidence in ontological knowledge bases. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 413–422 (2013)
Sadeghian, A., et al.: DRUM: end-to-end differentiable rule mining on knowledge graphs. arXiv:1911.00055 [cs.LG] (2019)
Das, R., et al.: Chains of reasoning over entities, relations, and text using recurrent neural networks. arXiv:1607.01426 [cs.CL] (2017)
Lao, N., et al.: Efficient relational learning with hidden variable detection. In: Proceedings of the 23rd International Conference on Neural Information Processing Systems - Volume 1, NIPS 2010, Vancouver, British Columbia, Canada, pp. 1234–1242. Curran Associates Inc. (2010)
Zhu, Z., et al.: Neural Bellman-Ford networks: a general graph neural network framework for link prediction. arXiv:2106.06935 [cs.LG] (2022)
Bordes, A., et al.: Translating embeddings for modeling multi-relational data. In: Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2, NIPS 2013, Lake Tahoe, Nevada, pp. 2787–2795. Curran Associates Inc. (2013)
Yang, B., et al.: Embedding entities and relations for learning and inference in knowledge bases. arXiv:1412.6575 [cs.CL] (2015)
Zhang, M., Chen, Y.: Link prediction based on graph neural networks. arXiv:1802.09691 [cs.LG] (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Huang, D., Zhao, G., Liu, T., Xu, T., Chen, E. (2023). Single Source Path-Based Graph Neural Network for Inductive Knowledge Graph Reasoning. In: Wang, H., Han, X., Liu, M., Cheng, G., Liu, Y., Zhang, N. (eds) Knowledge Graph and Semantic Computing: Knowledge Graph Empowers Artificial General Intelligence. CCKS 2023. Communications in Computer and Information Science, vol 1923. Springer, Singapore. https://doi.org/10.1007/978-981-99-7224-1_22
Download citation
DOI: https://doi.org/10.1007/978-981-99-7224-1_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7223-4
Online ISBN: 978-981-99-7224-1
eBook Packages: Computer ScienceComputer Science (R0)