FedRMS: Privacy-Preserving Federated Knowledge Graph Embedding Through Randomization
Lists
Only you see this
Abstract
Recent years have witnessed a growing interest in Federated Knowledge Graph Embedding, driven by its potential to leverage knowledge from various data owners to improve link prediction performance without the need for data sharing. Existing works typically assume that the central Federated Learning (FL) server owns a table containing unique entities/relations for all FL clients. In addition, all clients are assumed to use the same knowledge graph embedding method. However, these methods are vulnerable to privacy leakage and do not fully explore the different contributions of local entity embeddings. To bridge this gap, we propose a randomized embedding method selection approach for privacy-preserving federated knowledge graph embedding (FedRMS). It selects a knowledge graph embedding method for each client during the local training process with randomness and employs an attention-based aggregator to derive the global entity embedding on the FL server. Extensive experiments on three real-world public datasets demonstrate that FedRMS achieves significant improvements in terms of both privacy preservation and link prediction against 5 state-of-the-art methods.
BibTeX
@inproceedings{li2024fedrms,
author = {Qianyu Li and Xiaoli Tang and Siyao Zhou and Han Yu and Hengjie Song and Lizhen Cui and Xiaoxiao Li},
title = {{FedRMS: Privacy-Preserving Federated Knowledge Graph Embedding Through Randomization}},
booktitle = {ICME},
year = {2024},
doi = {10.1109/icme57554.2024.10688354},
}Loading related content...