无需微调，用超网络为非参与客户端生成适配模型
Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
- 用分布感知嵌入驱动超网络，分块生成专用模型
- 在多个数据集上性能优于现有方法，开销极低
- 适合资源受限且数据分布不同的边缘客户端
联邦学习（FL）作为一种保护隐私的协同学习范式备受关注，但数据异构性仍是关键挑战。现有方法虽能解决参与客户端的问题，却难以推广至具有域内分布偏移和资源限制的非参与客户端。为此，我们提出HyperFedZero，一种基于超网络的新方法，通过分布感知嵌入动态生成专用模型。该方法在前向传播中显式引入分布感知归纳偏置，采用增强型噪声嵌入提取器与平衡惩罚机制，有效防止特征坍缩。超网络利用这些嵌入逐块生成适配非参与客户端的专用模型，确保对独特数据分布的适应性。在多个数据集和模型上的实验表明，HyperFedZero表现卓越，持续超越对比方法，且计算、存储和通信开销极小。消融研究与可视化进一步验证了各组件必要性，证实了有意义的适应性与方法有效性。
原文摘要 · Abstract (English)
Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative learning, yet data heterogeneity remains a critical challenge. While existing methods achieve progress in addressing data heterogeneity for participating clients, they fail to generalize to non-participating clients with in-domain distribution shifts and resource constraints. To mitigate this issue, we present HyperFedZero, a novel method that dynamically generates specialized models via a hypernetwork conditioned on distribution-aware embeddings. Our approach explicitly incorporates distribution-aware inductive biases into the model's forward pass, extracting robust distribution embeddings using a NoisyEmbed-enhanced extractor with a Balancing Penalty, effectively preventing feature collapse. The hypernetwork then leverages these embeddings to generate specialized models chunk-by-chunk for non-participating clients, ensuring adaptability to their unique data distributions. Extensive experiments on multiple datasets and models demonstrate HyperFedZero's remarkable performance, surpassing competing methods consistently with minimal computational, storage, and communication overhead. Moreover, ablation studies and visualizations further validate the necessity of each component, confirming meaningful adaptations and validating the effectiveness of HyperFedZero.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。