Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation

Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, Lichao Sun


Abstract
Federated learning (FL) can be essential in knowledge representation, reasoning, and data mining applications over multi-source knowledge graphs (KGs). A recent study FedE first proposes an FL framework that shares entity embeddings of KGs across all clients. However, entity embedding sharing from FedE would incur a severe privacy leakage. Specifically, the known entity embedding can be used to infer whether a specific relation between two entities exists in a private client. In this paper, we introduce a novel attack method that aims to recover the original data based on the embedding information, which is further used to evaluate the vulnerabilities of FedE. Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE. Besides, relation embedding sharing can significantly reduce the communication cost due to its smaller size of queries. We conduct extensive experiments to evaluate FedR with five different KG embedding models and three datasets. Compared to FedE, FedR achieves similar utility and significant improvements regarding privacy-preserving effect and communication efficiency on the link prediction task.
Anthology ID:
2022.findings-emnlp.43
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
613–621
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.43
DOI:
10.18653/v1/2022.findings-emnlp.43
Bibkey:
Cite (ACL):
Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, and Lichao Sun. 2022. Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 613–621, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation (Zhang et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2022.findings-emnlp.43.pdf