发表机构
Mindlab（思维实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对联邦学习中动态特征漂移问题，提出FedCausal-Dyn框架，通过因果域特征分离和因果特征引导协作正则化实现可靠动态原型聚合，在三个联邦域泛化基准实验中取得最优性能，为该场景下的联邦学习提供解决方案。
AI 中文摘要
本文探讨联邦学习中动态特征漂移这一挑战性问题，即数据分布随客户端和时间演变，这在金融科技等现实应用中很常见。现有方法常假设静态漂移，在非平稳环境中效果受限。为克服此问题，我们提出FedCausal-Dyn，这是基于因果动态范式构建的新型联邦学习框架。其关键创新是因果域特征分离，通过专门投影头和对抗训练分离不变因果特征与虚假特定域变化，实现可靠动态原型聚合。还引入因果特征引导协作正则化，统一原型对比对齐和域不变性。在三个联邦域泛化基准上的大量实验表明，FedCausal-Dyn始终实现最优性能，消融研究证实各组件的关键贡献。我们的工作为动态特征漂移下的联邦学习提供了稳健且有原则的解决方案。
英文摘要
This paper addresses the challenging problem of dynamic feature drift in federated learning, where data distributions evolve across clients and over time -- a common scenario in real-world applications like financial technology. Existing approaches often assume static drift, limiting their effectiveness in non-stationary environments. To overcome this, we propose \textbf{FedCausal-Dyn}, a novel federated learning framework built on a causal-dynamic paradigm. Its key innovation is \textit{causal-domain feature separation}, which disentangles domain-invariant causal features from spurious, domain-specific variations via specialized projection heads and adversarial training. This enables \textit{reliable and dynamic prototype aggregation}, weighting local class prototypes by estimated reliability before global aggregation. We further introduce \textit{causal-feature guided collaborative regularization}, unifying prototype contrastive alignment and domain invariance into a cohesive objective. Extensive experiments on three federated domain generalization benchmarks demonstrate that FedCausal-Dyn consistently achieves state-of-the-art performance, with the highest average accuracy and the most stable results. Ablation studies confirm each component's critical contribution. Our work provides a robust and principled solution for federated learning under dynamic feature drift.
Comments18 pages
