通过共享生成能力实现跨域联邦学习，保护隐私且适应异构数据。
ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning
- 不传模型参数，仅交换生成能力，由服务器用合成数据训练。
- 在极端非独立同分布场景下仍保持高精度与隐私保护效果。
- 适合跨机构协作的隐私敏感场景，如医疗或金融数据联合建模。
我们提出ALIGN-FL，一种新型分布式学习方法，通过选择性共享生成组件来应对高度异构数据分布的挑战。与传统方式不同，该框架不交换完整模型参数，而是仅传输生成能力，由服务器使用合成样本进行全局训练。结合两种互补的隐私机制：自适应裁剪的DP-SGD和利普希茨正则化变分自编码器解码器，并支持异构客户端的状态化架构，在MNIST与Fashion-MNIST数据集上带有跨域异常值的实验验证了其有效性。分析表明，两种隐私机制能有效将敏感异常值映射为典型数据点，同时在典型的跨孤岛协作中保持模型性能。关键词：客户端无关学习、联邦学习（FL）、隐私保护生成模型、非独立同分布（Non-IID）、异构架构。
原文摘要 · Abstract (English)
We present ALIGN-FL, a novel approach to distributed learning that addresses the challenge of learning from highly disjoint data distributions through selective sharing of generative components. Instead of exchanging full model parameters, our framework enables privacy-preserving learning by transferring only generative capabilities across clients, while the server performs global training using synthetic samples. Through complementary privacy mechanisms: DP-SGD with adaptive clipping and Lipschitz regularized VAE decoders and a stateful architecture supporting heterogeneous clients, we experimentally validate our approach on MNIST and Fashion-MNIST datasets with cross-domain outliers. Our analysis demonstrates that both privacy mechanisms effectively map sensitive outliers to typical data points while maintaining utility in extreme Non-IID scenarios typical of cross-silo collaborations. Index Terms: Client-invariant Learning, Federated Learning (FL), Privacy-preserving Generative Models, Non-Independent and Identically Distributed (Non-IID), Heterogeneous Architectures
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。