Abstract
Few-shot knowledge graph completion (FKGC) task aims to predict unseen facts of a relation with few-shot reference entity pairs. Current approaches randomly select one negative sample for each reference entity pair to minimize a margin-based ranking loss, which easily leads to a zero-loss problem if the negative sample is far away from the positive sample and then out of the margin. Moreover, the entity should have a different representation under a different context. To tackle these issues, we propose a novel Relation-Aware Network with Attention-Based Loss (RANA) framework. Specifically, to better utilize the plentiful negative samples and alleviate the zero-loss issue, we strategically select relevant negative samples and design an attention-based loss function to further differentiate the importance of each negative sample. The intuition is that negative samples more similar to positive samples will contribute more to the model. Further, we design a dynamic relation-aware entity encoder for learning a context-dependent entity representation. Experiments demonstrate that RANA outperforms the state-of-the-art models on two benchmark datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bordes, A., Glorot, X., Weston, J., Bengio, Y.: A semantic matching energy function for learning with multi-relational data. Mach. Learn. 94(2), 233–259 (2014)
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NeurIPS vol. 26, pp. 2787–2795 (2013)
Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Hruschka, E., Mitchell, T.: Toward an architecture for never-ending language learning. In: AAAI, vol. 24, pp. 1306–1313 (2010)
Chen, M., Zhang, W., Zhang, W., Chen, Q., Chen, H.: Meta relational learning for few-shot link prediction in knowledge graphs. In: EMNLP-IJCNLP, pp. 4217–4226 (2019)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126–1135. PMLR (2017)
Kazemi, S.M., Poole, D.: Simple embedding for link prediction in knowledge graphs. In: NeurIPS 31 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: ICML (2011)
Niu, G., et al.: Relational learning with gated and attentive neighbor aggregator for few-shot knowledge graph completion. In: SIGIR, pp. 213–222 (2021)
Rong, Y., Huang, W., Xu, T., Huang, J.: DropEdge: towards deep graph convolutional networks on node classification. In: ICLR (2019)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: A unified embedding for face recognition and clustering. In: CVPR, pp. 815–823 (2015)
Sheng, J., Guo, S., Chen, Z., Yue, J., Wang, L., Liu, T., Xu, H.: Adaptive attentional network for few-shot knowledge graph completion. In: EMNLP, pp. 1681–1691 (2020)
Sun, Z., Deng, Z.H., Nie, J.Y., Tang, J.: Rotate: Knowledge graph embedding by relational rotation in complex space. In: ICLR (2018)
Tang, Z., et al.: Positive-unlabeled learning with adversarial data augmentation for knowledge graph completion. In: IJCAI, pp. 1935–1942 (2022)
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML, pp. 2071–2080. PMLR (2016)
Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. In: CACM (2014)
Wu, H., Yin, J., Rajaratnam, B., Guo, J.: Hierarchical relational learning for few-shot knowledge graph completion. arXiv preprint arXiv:2209.01205 (2022)
Xiong, W., Yu, M., Chang, S., Guo, X., Wang, W.Y.: One-shot relational learning for knowledge graphs. In: EMNLP, pp. 1980–1990 (2018)
Yang, B., Yih, S.W.T., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: ICLR (2015)
Yang, S., Tian, J., Zhang, H., Yan, J., He, H., Jin, Y.: TransMS: knowledge graph embedding for complex relations by multidirectional semantics. In: IJCAI, pp. 1935–1942 (2019)
Yang, Z., Ding, M., Zhou, C., Yang, H., Zhou, J., Tang, J.: Understanding negative sampling in graph representation learning. In: SIGKDD, pp. 1666–1676 (2020)
Zha, H., Chen, Z., Yan, X.: Inductive relation prediction by BERT. In: AAAI (2022)
Zhang, C., Yao, H., Huang, C., Jiang, M., Li, Z., Chawla, N.V.: Few-shot knowledge graph completion. In: AAAI 34, 3041–3048 (2020)
Zhou, K., Li, Y., Li, Q.: Distantly supervised named entity recognition via confidence-based multi-class positive and unlabeled learning. In: ACL, pp. 7198–7211 (2022)
Zhou, K., Qiao, Q., Li, Y., Li, Q.: Improving distantly supervised relation extraction by natural language inference. arXiv preprint arXiv:2208.00346 (2022)
Acknowledgement
The work is supported in part by NSF IIS-2007941.
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
Qiao, Q., Li, Y., Zhou, K., Li, Q. (2023). Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13937. Springer, Cham. https://doi.org/10.1007/978-3-031-33380-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-33380-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33379-8
Online ISBN: 978-3-031-33380-4
eBook Packages: Computer ScienceComputer Science (R0)