Efficient Federated Domain Translation
Efficient Federated Domain Translation
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Zeyu Zhou;Sheikh Shams Azam;Christopher G. Brinton;David I. Inouye
中科院分区：
文献类型：
--
作者：
Zeyu Zhou;Sheikh Shams Azam;Christopher G. Brinton;David I. Inouye
联邦学习（FL）的一个中心主题是客户端数据分布通常不是独立和相同分布（IID），这对训练过程有很大的影响。虽然大多数现有的FL算法关注的是传统的非iid设置，即客户端之间的类不平衡或缺失类，但在实践中，分布差异可能会更复杂，例如，类条件（域）分布的变化。在本文中，我们考虑了FL中的这种复杂情况，其中每个客户端只能访问一个域分布。对于域泛化等任务，大多数现有的学习算法需要在训练期间访问来自多个客户端（即来自多个域）的数据，这在FL中是禁止的。为了解决这一挑战，我们提出了一种联邦域翻译方法，该方法为每个客户端生成伪数据，这可能对多个下游学习任务有用。我们的经验证明，我们的翻译模型更具有资源效率（在通信和计算方面），并且比标准领域翻译方法更容易在FL设置中训练。此外，我们证明了学习翻译模型能够在联邦设置中使用最先进的领域泛化方法，与现有方法相比，它提高了同步周期增加的准确性和鲁棒性。
A central theme in federated learning (FL) is the fact that client data distributions are often not independent and identically distributed (IID), which has strong implications on the training process. While most existing FL algorithms focus on the conventional non-IID setting of class imbalance or missing classes across clients, in practice, the distribution differences could be more complex, e.g., changes in class conditional (domain) distributions. In this paper, we consider this complex case in FL wherein each client has access to only one domain distribution. For tasks such as domain generalization, most existing learning algorithms require access to data from multiple clients (i.e., from multiple domains) during training, which is prohibitive in FL. To address this challenge, we propose a federated domain translation method that generates pseudodata for each client which could be useful for multiple downstream learning tasks. We empirically demonstrate that our translation model is more resource-efficient (in terms of both communication and computation) and easier to train in an FL setting than standard domain translation methods. Furthermore, we demonstrate that the learned translation model enables use of state-of-the-art domain generalization methods in a federated setting, which enhances accuracy and robustness to increases in the synchronization period compared to existing methodology.