arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.04888cs.LGcs.CV
收藏

基于联邦采样Softmax的高效图像表示学习

Efficient Image Representation Learning with Federated Sampled Softmax

Google Research(谷歌研究院)

Sagar M. Waghmare, Hang Qi, Huizhong Chen, Mikhail Sirotenko, Tomer Meron

摘要:

在分散数据上学习图像表示可以在数据无法跨数据孤岛聚合的情况下带来许多好处。Softmax交叉熵损失非常有效,通常用于学习图像表示。使用大量的类已被证明是特别有益的描述能力,这种表示在集中式学习。然而,使用联邦学习在分散的数据上这样做并不简单,因为对FL客户端的计算和通信的需求与类的数量成比例地增加。在这项工作中,我们介绍了联邦采样softmax(FedSS),一个资源有效的方法,学习图像表示与联邦学习。具体而言,FL客户端对一组类进行采样,并仅针对近似全局完整softmax目标的采样softmax目标优化相应的模型参数。我们研究了损失公式,并根据经验表明,我们的方法显着减少了传输到客户端设备并由客户端设备优化的参数数量,同时与标准的全softmax方法相当。这项工作为在联邦设置下有效地学习具有大量类的分散数据上的图像表示创造了可能性。

英文摘要:

Learning image representations on decentralized data can bring many benefits in cases where data cannot be aggregated across data silos. Softmax cross entropy loss is highly effective and commonly used for learning image representations. Using a large number of classes has proven to be particularly beneficial for the descriptive power of such representations in centralized learning. However, doing so on decentralized data with Federated Learning is not straightforward as the demand on FL clients' computation and communication increases proportionally to the number of classes. In this work we introduce federated sampled softmax (FedSS), a resource-efficient approach for learning image representation with Federated Learning. Specifically, the FL clients sample a set of classes and optimize only the corresponding model parameters with respect to a sampled softmax objective that approximates the global full softmax objective. We examine the loss formulation and empirically show that our method significantly reduces the number of parameters transferred to and optimized by the client devices, while performing on par with the standard full softmax method. This work creates a possibility for efficiently learning image representations on decentralized data with a large number of classes under the federated setting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑