基于 Fisher 信息剪枝的领域敏感联邦学习
Domain Sensitive Federated Learning with Fisher-Informed Pruning
把 Fisher 信息当作逐域通道重要性信号，在联邦场景下生成共享剪枝掩码并按域重激活通道，可迁移到视觉模型的多域个性化压缩与结构对齐；结构对比损失利用域原型增强域内一致性与域间可分性，对多域视觉表征学习有直接参考价值。
原文依据 estimates channel importance per domain via Fisher information, and uploads this signal to the server to obtain a globally shared pruning mask
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦学习（FL）是一种重要的分布式训练范式，使设备能够利用本地数据协作训练共享模型。然而在实际中，客户端通常持有来自多个分布领域的数据，这给效率与泛化带来了显著挑战。本文提出一种领域敏感的联邦剪枝框架 FedFIP，在保留领域特定表示的同时维护领域不变结构。领域敏感 Fisher 剪枝（DSFP）模块通过 Fisher 信息估计每个领域的通道重要性，并将该信号上传至服务器以获得全局共享的剪枝掩码。考虑到本地领域异质性，每个客户端复用其 Fisher 信息来选择性地重新激活领域特定通道，从而得到结构上保持对齐、又能适应本地异质性的个性化稀疏模型。为进一步提升性能，我们采用领域敏感正则化（DSR）模块：服务器根据上传的重要性信号构建领域原型并将其广播回客户端。在领域原型的引导下，我们采用结构对比损失来增强域内一致性与域间可判别性。我们提出一种结构感知聚合算法，将异构的个性化架构融合为领域泛化的全局模型。在多领域基准上的实验表明，FedFIP 在显著缩小模型规模的同时超越了最优的联邦学习基线。
英文原文摘要 1521 字符
Federated Learning (FL) serves as a prominent distributed training paradigm, enabling devices to collaboratively train a shared model with local data. However, in practice, clients generally possess data from multiple distributional domains, posing significant challenges to efficiency and generalization. In this paper, we propose a domain-sensitive federated pruning framework, FedFIP, that preserves domain-invariant structures while retaining domain-specific representations. The Domain-Sensitive Fisher Pruning (DSFP) module estimates channel importance per domain via Fisher information, and uploads this signal to the server to obtain a globally shared pruning mask. Given local domain heterogeneity, each client reuses its Fisher information to selectively reactivate domain-specific channels, yielding personalized sparse models that remain structurally aligned yet adapt to local heterogeneity. To further enhance performance, we adopt a Domain-Sensitive Regularization (DSR) module: the server builds domain prototypes from uploaded importance signals and broadcasts them back. Guided by the domain prototypes, we adopt a structure-contrastive loss to strengthen intra-domain consistency and inter-domain discriminability. We propose a structure-aware aggregation algorithm that fuses heterogeneous personalized architectures into a domain-generalized global model. Experiments on multi-domain benchmarks demonstrate that FedFIP surpasses state-of-the-art FL baselines while substantially shrinking model size.