联邦图遗忘学习
Federated Graph Unlearning
AI总结：
针对联邦图学习中的被遗忘权问题，提出统一框架，采用原型梯度与对抗图生成的双策略，分别处理元遗忘和客户端遗忘，显著提升预测精度与遗忘效果。
摘要：
数据隐私的需求催生了联邦图学习（FGL）等框架的发展，这些框架促进了去中心化的模型训练。然而，此类系统中的一个重大操作挑战是遵守“被遗忘权”。这一原则要求针对两种不同类型的数据删除建立稳健的机制：从局部子图中选择性擦除特定实体及其相关知识，以及彻底移除用户的整个数据集及其影响。现有方法往往难以完全满足这两种遗忘需求，经常导致数据删除不完整或系统中残留知识持续存在。本工作引入了一个统一框架，旨在为这些挑战提供全面的解决方案。所提出的框架采用了一种针对特定遗忘请求量身定制的双管齐下策略。对于细粒度的元遗忘，它使用原型梯度来指导初始的局部遗忘过程，随后通过生成对抗图来细化，以消除受影响客户端之间任何剩余的数据痕迹。在完全客户端遗忘的情况下，该框架仅利用对抗图生成来从剩余网络中清除已离开客户端的贡献。在多个基准数据集上进行的大量实验验证了所提出的方法。与现有方法相比，该框架在客户端和元遗忘场景中均实现了模型预测准确性的显著提升。此外，额外的研究证实了其作为即插即用模块的实用性，它显著增强了其他既有方法的预测能力和遗忘效果。
英文摘要：
The demand for data privacy has led to the development of frameworks like Federated Graph Learning (FGL), which facilitate decentralized model training. However, a significant operational challenge in such systems is adhering to the right to be forgotten. This principle necessitates robust mechanisms for two distinct types of data removal: the selective erasure of specific entities and their associated knowledge from local subgraphs and the wholesale removal of a user's entire dataset and influence. Existing methods often struggle to fully address both unlearning requirements, frequently resulting in incomplete data removal or the persistence of residual knowledge within the system. This work introduces a unified framework, conceived to provide a comprehensive solution to these challenges. The proposed framework employs a bifurcated strategy tailored to the specific unlearning request. For fine-grained Meta Unlearning, it uses prototype gradients to direct the initial local forgetting process, which is then refined by generating adversarial graphs to eliminate any remaining data traces among affected clients. In the case of complete client unlearning, the framework utilizes adversarial graph generation exclusively to purge the departed client's contributions from the remaining network. Extensive experiments on multiple benchmark datasets validate the proposed approach. The framework achieves substantial improvements in model prediction accuracy across both client and meta-unlearning scenarios when compared to existing methods. Furthermore, additional studies confirm its utility as a plug-in module, where it materially enhances the predictive capabilities and unlearning effectiveness of other established methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
