提出SAFLe框架，实现单轮高效非线性联邦学习。
Single-Round Scalable Analytic Federated Learning
- 用分桶特征与稀疏分组嵌入构建非线性结构
- 在所有基准上显著超越线性AFL和多轮DeepAFL
- 适合大规模异构数据下的高效联邦视觉任务
联邦学习面临通信开销高和异构数据下性能下降两大挑战。解析联邦学习（AFL）提供单轮、数据分布无关的解决方案，但仅适用于线性模型。后续非线性方法如DeepAFL虽恢复精度，却牺牲了单轮优势。本文提出SAFLe框架，通过引入分桶特征与稀疏分组嵌入，实现可扩展的非线性表达能力。我们证明该非线性架构在数学上等价于高维线性回归，从而可沿用AFL的单次聚合法则。实验证明，SAFLe在所有基准上均达到解析联邦学习新纪录，显著优于线性AFL和多轮DeepAFL，为联邦视觉任务提供了高效可扩展的解决方案。
原文摘要 · Abstract (English)
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.
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。