Federated Learning (FL) recently emerges as a paradigm to train a global machine learning model across distributed clients without sharing raw data. Knowledge Graph (KG) embedding represents KGs in a continuous vector space, serving as the backbone of many knowledge-driven applications. As a promising combination, federated KG embedding can fully take advantage of knowledge learned from different clients while preserving the privacy of local data. However, realistic problems such as data heterogeneity and knowledge forgetting still remain to be concerned. In this paper, we propose FedLU, a novel FL framework for heterogeneous KG embedding learning and unlearning. To cope with the drift between local optimization and global convergence caused by data heterogeneity, we propose mutual knowledge distillation to transfer local knowledge to global, and absorb global knowledge back. Moreover, we present an unlearning method based on cognitive neuroscience, which combines retroactive interference and passive decay to erase specific knowledge from local clients and propagate to the global model by reusing knowledge distillation. We construct new datasets for assessing realistic performance of the state-of-the-arts. Extensive experiments show that FedLU achieves superior results in both link prediction and knowledge forgetting.

翻译：联邦学习（FL）近期作为一种无需共享原始数据即可在分布式客户端间训练全局机器学习模型的范式兴起。知识图谱（KG）嵌入将知识图谱表示在连续向量空间中，是众多知识驱动应用的基石。作为一种有前景的组合，联邦知识图谱嵌入可充分利用来自不同客户端的学习知识，同时保护本地数据的隐私。然而，诸如数据异构性和知识遗忘等现实问题仍有待关注。本文提出FedLU，一种用于异构知识图谱嵌入学习与遗忘的新型FL框架。为应对数据异构性导致的本地优化与全局收敛之间的偏移，我们提出互知识蒸馏，将本地知识迁移至全局，并吸收全局知识回传至本地。此外，我们提出一种基于认知神经科学的遗忘方法，结合逆向干扰与被动衰减，从本地客户端擦除特定知识，并通过复用知识蒸馏将其传播至全局模型。我们构建了用于评估现有方法实际性能的新数据集。大量实验表明，FedLU在链接预测与知识遗忘两方面均取得优越结果。