Federated Knowledge Graph Unlearning via Diffusion Model

TL;DR

This paper introduces FedDM, a diffusion model-based framework for machine unlearning in federated knowledge graphs, effectively forgetting specific data influences while maintaining overall model performance.

Contribution

We propose FedDM, a novel diffusion model approach for machine unlearning in federated knowledge graph embeddings, balancing data forgetting and model accuracy.

Findings

FedDM effectively forgets specific knowledge influences.

Experimental results show maintained overall model performance.

Promising results on benchmark datasets.

Abstract

Federated learning (FL) promotes the development and application of artificial intelligence technologies by enabling model sharing and collaboration while safeguarding data privacy. Knowledge graph (KG) embedding representation provides a foundation for knowledge reasoning and applications by mapping entities and relations into vector space. Federated KG embedding enables the utilization of knowledge from diverse client sources while safeguarding the privacy of local data. However, due to demands such as privacy protection and the need to adapt to dynamic data changes, investigations into machine unlearning (MU) have been sparked. However, it is challenging to maintain the performance of KG embedding models while forgetting the influence of specific forgotten data on the model. In this paper, we propose FedDM, a novel framework tailored for machine unlearning in federated knowledge graphs. Leveraging diffusion models, we generate noisy data to sensibly mitigate the influence of specific knowledge on FL models while preserving the overall performance concerning the remaining data. We conduct experimental evaluations on benchmark datasets to assess the efficacy of the proposed model. Extensive experiments demonstrate that FedDM yields promising results in knowledge forgetting.