arxiv.org·2026/10/23·Thanh Linh Nguyen / Quoc-Viet Pham
为什么重要 用路径依赖客户端选择减少联邦遗忘学习所需客户端、通信与计算，对联邦学习中的遗忘请求处理有工程参考价值。
联邦遗忘学习（FU）旨在从已训练模型中移除指定目标客户端的影响，而无需承担从头重训的高昂成本。现有方法在很大程度上把遗忘学习视为一种后处理、无状态操作，忽略了客户端影响是路径依赖的：训练期间作出的贡献，尤其是在关键学习期（CLP）期间的贡献，可能产生不成比例且持久的影响。此外，知识重叠和客户端间歇性可用，使依赖所有保留客户端既低效又不实际。
我们引入 PDF，一个路径依赖的客户端选择框架，其基于这样的洞察：保留客户端对遗忘学习的价值并不相同。在训练期间，PDF维护轻量、目标无关、CLP 加权的历史，概括每个客户端累积的更新方向和与全局模型的对齐程度。在收到遗忘请求时，这些历史识别并排序那些全局信息丰富但与目标弱耦合的保留客户端，从而只用 top-k 客户端在少量轮次内进行基于重训的遗忘学习。
在 FMNIST、CIFAR-10 和 CIFAR-100 上，在 IID 和 non-IID 设置下的实验表明，PDF用显著更少的保留客户端实现了有效遗忘和强保留效用。特别地，PDF在 non-IID CIFAR-10 上实现 0% 遗忘准确率，并具有类似重训的 MIA AUC，在 CIFAR-100 上较最强竞争 FU 基线将保留准确率提升最多 6.91 个百分点，并相对 Retrain 将通信减少约 69%，将计算减少 57--61%。
Federated unlearning (FU) aims to remove a designated target client's influence from a trained model without the prohibitive cost of retraining from scratch.
Existing methods largely treat unlearning as a post-hoc, stateless operation, overlooking that client influence is path-dependent: contributions made during training, particularly during critical learning periods (CLPs), can have disproportionate and persistent effects.
Moreover, knowledge overlap and intermittent client availability make relying on all retained clients inefficient and impractical.
We introduce PDF, a path-dependent client-selection framework based on the insight that retained clients are not equally valuable for unlearning.
During training, PDF maintains lightweight, target-agnostic, CLP-weighted histories summarizing each client's accumulated update direction and global-model alignment.
Upon an unlearning request, these histories identify and rank retained clients that are globally informative yet weakly coupled to the target, enabling retraining-based unlearning with only the top-k clients over a small number of rounds.
Experiments on FMNIST, CIFAR-10, and CIFAR-100 under IID and non-IID settings show that PDF achieves effective forgetting and strong retained utility with substantially fewer retained clients.
In particular, PDF achieves 0% forgetting accuracy with retraining-like MIA AUC on non-IID CIFAR-10, improves retained accuracy by up to 6.91 percentage points over the strongest competing FU baseline on CIFAR-100, and reduces communication by approximately 69% and computation by 57--61% relative to Retrain.
原版排版与图表 · 手机无法内嵌时可在浏览器打开。PDF 插件内选文不能传给网页助手。