Abstract
Due to the problem of privacy protection, it is very limited to apply distributed representation learning to practical applications in the scenario of multi-party cooperation. Federated learning is an emerging feasible solution to solve the issue of data security. However, due to the heterogeneity of the data from multi-party platforms, it is not easy to employ federated learning directly to embed multi-party data. In this paper, we propose a new federated framework FKE for representation learning of knowledge graphs to deal with the problem of privacy protection and heterogeneous data. Experiments show that the FKE can perform well in typical link prediction, overcome the problem of heterogeneous data and have a significant effect.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Gutierrez, C., Sequeda, J.: Knowledge graphs. Commun. ACM. 64(3), 96–104 (2021)
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: 27th Annual Conference on Neural Information Processing Systems (NIPS), pp. 2787–2795 (2013)
Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: 28th AAAI Conference on Artificial Intelligence (AAAI), pp. 1112–1119 (2014)
Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: 29th AAAI Conference on Artificial Intelligence (AAAI), pp. 2181–2187 (2015)
Nickel, M., Rosasco, L., Poggio, T.: Holographic embeddings of knowledge graphs. In: 30th AAAI Conference on Artificial Intelligence (AAAI), pp. 1955–1961 (2016)
Yang, B., Yih, W., He, X., Gao, J., and Deng, L.: Embedding Entities and Relations for learning and inference in knowledge bases. In: 3rd International Conference on Learning Representations (ICLR), Poster (2015)
Glorot, X., Bordes, A., Weston, J., Bengio, Y.: A semantic matching energy function for learning with multi-relational data. Mach. Learn. 94(2), 233–259 (2014)
Socher, R., Chen, D., Manning, C., Ng, A.: Reasoning with neural tensor networks for knowledge base completion. In: 27th Annual Conference on Neural Information Processing Systems (NIPS), pp. 926–934 (2013)
Shi, B., Weninger, T.: Embedding projection for knowledge graph completion. In: 31st AAAI Conference on Artificial Intelligence (AAAI), pp. 1236–1242 (2017)
Nathani, D., Chauhan, J., Sharma, C., Kaul, M.: Learning attention-based embeddings for relation prediction in knowledge graphs. In: 57th Annual Meeting of the Association for Computational Linguistics on Proceedings (ACL), pp. 4710–4723 (2019)
Li, M., Andersen, D.G., Park, J.W., Smola, A.J.: Scaling distributed machine learning with the parameter server. In: 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI), pp. 583–598 (2014)
Kairouz, P., et al.: Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977 (2019)
Brendan, H., Moore, E., Ramage, D., Hampson, S., Agüera y Arcas, B.: Communication-efficient learning of deep networks from decentralized data. In: 20th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 54–55 (2017)
TensorFlow Federated. https://www.tensorflow.org/federated
Federated AI technology enabler. https://www.fedai.org/
Brakerski, Z., Gentry, C., Vaikuntanathan, V.: Leveled fully homomorphic encryption without bootstrapping. ACM Trans. Comput. Theory. 6(3), 1–36 (2014)
Cheu, A., Smith, A., Ullman, J., Zeber, D., Zhilyaev, M.: Distributed differential privacy via shuffling. In: 38th Annual International Conference on the Theory and Applications of Cryptographic Techniques, pp. 375–403 (2019)
Wang, H.: Federated learning with matched averaging. In: 8th International Conference on Learning Representations (ICLR), Poster (2020)
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. In: Machine Learning and Systems, poster (2020)
Nickel, M., Tresp, V.: Tensor factorization for multi-relational learning. In: Machine Learning and Knowledge Discovery in Databases - European Conference, pp. 23–27 (2013)
Acknowledgments
The work described in this paper is supported by Shenzhen Science and Technology Foundation (JCYJ20170816093943197).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Meng, W., Chen, S., Feng, Z. (2021). Federated Knowledge Graph Embeddings with Heterogeneous Data. In: Qin, B., Jin, Z., Wang, H., Pan, J., Liu, Y., An, B. (eds) Knowledge Graph and Semantic Computing: Knowledge Graph Empowers New Infrastructure Construction. CCKS 2021. Communications in Computer and Information Science, vol 1466. Springer, Singapore. https://doi.org/10.1007/978-981-16-6471-7_2
Download citation
DOI: https://doi.org/10.1007/978-981-16-6471-7_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6470-0
Online ISBN: 978-981-16-6471-7
eBook Packages: Computer ScienceComputer Science (R0)