Abstract
Most personalised federated learning (FL) approaches assume that raw data of all clients are defined in a common subspace i.e. all clients store their data according to the same schema. For real-world applications, this assumption is restrictive as clients, having their own systems to collect and then store data, may use heterogeneous data representations. We aim at filling this gap. To this end, we propose a general framework coined FLIC that maps client's data onto a common feature space via local embedding functions. The common feature space is learnt in a federated manner using Wasserstein barycenters while the local embedding functions are trained on each client via distribution alignment. We integrate this distribution alignement mechanism into a federated learning approach and provide the algorithmics of FLIC. We compare its performances against FL benchmarks involving heterogeneous input features spaces. In addition, we provide theoretical insights supporting the relevance of our methodology.
Abstract (translated)
大多数个性化联邦学习(FL)方法假设所有客户的 raw 数据都在一个共同子空间中定义,即所有客户按照相同的 schema 存储数据。对于现实世界的应用,这种假设是限制性的,因为客户可能使用自己的系统收集和存储数据,并使用不同类型的数据表示。我们的目标是填补这个差距。为此,我们提出了一个通用的框架,称为 FLIC,它通过 local embedding 函数将客户的数据映射到共同特征空间中。共同特征空间使用 Wasserstein 均值中心学习,而本地嵌入函数通过分布对齐对每个客户进行训练。我们将分布对齐机制融入联邦学习方法中,并提供了 FLIC 的算法。我们比较了 FLIC 的性能与涉及不同类型的输入特征空间的FL基准测试。此外,我们提供了支持我们方法相关性的理论 insights。
URL
https://arxiv.org/abs/2301.11447