Abstract
Few-shot knowledge graph completion (FKGC) has drawn growing research attention recently, aiming at inferring new triples using only a small number of related references. Most existing FKGC methods encode few-shot relations by capturing signals from local neighbors of each entity. However, this process dramatically relies on a thorough background knowledge graph (background KG) that is space-consuming to storage and often inaccessible in real-life cases. Moreover, they tend to overlook the underlying correlational information coming with different relations. In this paper, we attempt to address FKGC task in a practical scenario where background KG is not provided and propose a novel framework called ICOM (I Can Count On Myself) which aims at making full use of few-shot instances within and across relations. Specifically, we go deep into the interaction between entity pairs within specific relation and devise a 3D convolutional meta-relation learner to extract relation-specific features straightly from triple. To accumulate knowledge across relations, an analogical enhancer is then built to leverage the semantic relational correlations attentively so that correlative relations can complement each other on representation learning for better link prediction. Finally, we introduce meta-learning technique for faster adaption. Empirical studies on three real-world FKGC datasets demonstrate that ICOM shows superiority over competitive baseline methods and achieves new state-of-the-art results with different few-shot sizes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS (2013)
Chen, M., Zhang, W., Zhang, W., Chen, Q., Chen, H.: Meta relational learning for few-shot link prediction in knowledge graphs. arXiv abs/1909.01515 (2019)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. In: AAAI Conference on Artificial Intelligence (2017)
Feng, W.H., Zha, D., Wang, L., Guo, X.: Convolutional 3D embedding for knowledge graph completion. In: 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp. 1197–1202 (2022)
Gabrilovich, E., Markovitch, S.: Wikipedia-based semantic interpretation for natural language processing. J. Artif. Intell. Res. 34, 443–498 (2014)
Jiang, Z., Gao, J., Lv, X.: Metap: meta pattern learning for one-shot knowledge graph completion. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (2021)
Li, Y., Yu, K., Zhang, Y., Wu, X.: Learning relation-specific representations for few-shot knowledge graph completion. arXiv abs/2203.11639 (2022)
Liang, Y., Zhao, S., Cheng, B., Yin, Y., Yang, H.: Tackling solitary entities for few-shot knowledge graph completion. In: Knowledge Science, Engineering and Management (2022)
van der Maaten, L., Hinton, G.E.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Niu, G., et al.: Relational learning with gated and attentive neighbor aggregator for few-shot knowledge graph completion. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (2021)
Sheng, J., et al.: Adaptive attentional network for few-shot knowledge graph completion. In: Conference on Empirical Methods in Natural Language Processing (2020)
Sun, Z., Deng, Z., Nie, J.Y., Tang, J.: Rotate: knowledge graph embedding by relational rotation in complex space. arXiv abs/1902.10197 (2018)
Tian, A., Zhang, C., Rang, M., Yang, X., Zhan, Z.: RA-GCN: relational aggregation graph convolutional network for knowledge graph completion. In: Proceedings of the 2020 12th International Conference on Machine Learning and Computing (2020)
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: International Conference on Machine Learning (2016)
Wang, Y., Zhang, H.: Introducing graph neural networks for few-shot relation prediction in knowledge graph completion task. In: Knowledge Science, Engineering and Management (2021)
Xiong, W., Yu, M., Chang, S., Guo, X., Wang, W.Y.: One-shot relational learning for knowledge graphs. In: Conference on Empirical Methods in Natural Language Processing (2018)
Yang, B., tau Yih, W., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. CoRR abs/1412.6575 (2014)
Yuan, X., Xu, C., Li, P., Chen, Z.: Relational learning with hierarchical attention encoder and recoding validator for few-shot knowledge graph completion. In: Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing (2022)
Zhang, C., Yao, H., Huang, C., Jiang, M., Li, Z.J., Chawla, N.: Few-shot knowledge graph completion. In: AAAI Conference on Artificial Intelligence (2019)
Zhang, N., et al.: Long-tail relation extraction via knowledge graph embeddings and graph convolution networks. In: North American Chapter of the Association for Computational Linguistics (2019)
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 Switzerland AG
About this paper
Cite this paper
Yang, R., Wei, X. (2023). Dealing with Over-Reliance on Background Graph for Few-Shot Knowledge Graph Completion. In: Jin, Z., Jiang, Y., Buchmann, R.A., Bi, Y., Ghiran, AM., Ma, W. (eds) Knowledge Science, Engineering and Management. KSEM 2023. Lecture Notes in Computer Science(), vol 14117. Springer, Cham. https://doi.org/10.1007/978-3-031-40283-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-40283-8_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40282-1
Online ISBN: 978-3-031-40283-8
eBook Packages: Computer ScienceComputer Science (R0)