单轮可扩展解析联邦学习
Single-Round Scalable Analytic Federated Learning
SAFLe 把非线性模型等价改写为高维线性回归，从而复用解析 FL 的单轮闭式聚合；做视觉联邦训练时可直接套用这一「分桶特征 + 稀疏分组嵌入」检测头，在 non-IID 客户端上省掉多轮通信。
原文依据 We prove this non-linear architecture is mathematically equivalent to a high-dimensional linear regression.
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）受两个关键挑战困扰：高通信开销以及在异构（非独立同分布）数据上的性能崩溃。解析联邦学习（AFL）提供了一种单轮、对数据分布不变的解决方案，但仅限于线性模型。此后的非线性方法（如 DeepAFL）恢复了精度，却牺牲了单轮优势。在本工作中，我们打破了这一权衡。我们提出 SAFLe，一个通过引入由分桶特征构成的结构化检测头以及稀疏分组嵌入来实现可扩展非线性表达能力的框架。我们证明该非线性架构在数学上等价于高维线性回归。这一关键等价性使 SAFLe 能够用 AFL 的单次、不变聚合律求解。在实验上，SAFLe 确立了分析式联邦学习的最优性能，在所有基准上精度显著优于线性 AFL 与多轮 DeepAFL，展示了面向联邦视觉的高效且可扩展的解决方案。
英文原文摘要 1020 字符
Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-round, data distribution invariant solution, but is limited to linear models. Subsequent non-linear approaches, like DeepAFL, regain accuracy but sacrifice the single-round benefit. In this work, we break this trade-off. We propose SAFLe, a framework that achieves scalable non-linear expressivity by introducing a structured head of bucketed features and sparse, grouped embeddings. We prove this non-linear architecture is mathematically equivalent to a high-dimensional linear regression. This key equivalence allows SAFLe to be solved with AFL's single-shot, invariant aggregation law. Empirically, SAFLe establishes a new state-of-the-art for analytic FL, significantly outperforming both linear AFL and multi-round DeepAFL in accuracy across all benchmarks, demonstrating a highly efficient and scalable solution for federated vision.