Summary of Federated Knowledge Graph Unlearning Via Diffusion Model, by Bingchen Liu and Yuanyuan Fang
Federated Knowledge Graph Unlearning via Diffusion Model
by Bingchen Liu, Yuanyuan Fang
First submitted to arxiv on: 13 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Federated learning (FL) is a technique for developing and applying artificial intelligence technologies while safeguarding data privacy by enabling model sharing and collaboration. 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, machine unlearning (MU) investigations have been sparked due to demands such as privacy protection and adapting to dynamic data changes. The challenge lies in maintaining the performance of KG embedding models while forgetting the influence of specific forgotten data on the model. To address this, we propose FedDM, a novel framework tailored for machine unlearning in federated knowledge graphs, leveraging diffusion models to generate noisy data that mitigates the influence of specific knowledge on FL models while preserving overall performance concerning remaining data. We conduct experimental evaluations on benchmark datasets to assess the efficacy of the proposed model, demonstrating promising results in knowledge forgetting. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Artificial intelligence (AI) is a way for computers to learn and get better at tasks without being explicitly programmed. Federated learning lets different devices or machines share and work together with AI models while keeping their own data private. Knowledge graphs are like maps of information that can be used to reason and make decisions. When we want to forget certain information, it’s hard to balance forgetting some things while still using the rest. In this paper, we propose a new way called FedDM to help machines forget specific knowledge without ruining their overall performance. We test our idea on different datasets and show that it works well. |
Keywords
* Artificial intelligence * Embedding * Federated learning * Knowledge graph * Vector space
