首个专为联邦学习设计的商用图像数据集及两种新算法
Federated Learning for Commercial Image Sources
- 提出环形与星型联邦学习拓扑，解决数据异构问题
- 在23,326张商用图像上，性能优于现有基线方法
- 适合研究隐私保护图像分类的开发者与研究人员
联邦学习是一种协作式机器学习范式，允许多个客户端在不共享数据的情况下协同训练全局模型，从而提供具备隐私保护能力的安全学习平台。本文引入一个包含23,326张图像的新数据集，这些图像来自八个不同的商用来源，并分为31个类别，与Office-31数据集类似。据我们所知，这是首个专为联邦学习设计的图像分类数据集。同时，本文提出了两种新的联邦学习算法：Fed-Cyclic 和 Fed-Star。在 Fed-Cyclic 中，客户端从其前一个客户端接收权重，通过本地训练更新后传递给下一个客户端，形成环状拓扑结构。在 Fed-Star 中，客户端从所有其他客户端接收权重，通过预聚合（以缓解统计异构性）和本地训练更新权重，再将更新后的本地权重发送给所有其他客户端，形成星型拓扑结构。实验结果表明，这两种算法在新引入的数据集上均优于现有基线方法。
原文摘要 · Abstract (English)
Federated Learning is a collaborative machine learning paradigm that enables multiple clients to learn a global model without exposing their data to each other. Consequently, it provides a secure learning platform with privacy-preserving capabilities. This paper introduces a new dataset containing 23,326 images collected from eight different commercial sources and classified into 31 categories, similar to the Office-31 dataset. To the best of our knowledge, this is the first image classification dataset specifically designed for Federated Learning. We also propose two new Federated Learning algorithms, namely Fed-Cyclic and Fed-Star. In Fed-Cyclic, a client receives weights from its previous client, updates them through local training, and passes them to the next client, thus forming a cyclic topology. In Fed-Star, a client receives weights from all other clients, updates its local weights through pre-aggregation (to address statistical heterogeneity) and local training, and sends its updated local weights to all other clients, thus forming a star-like topology. Our experiments reveal that both algorithms perform better than existing baselines on our newly introduced dataset.
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。