论文标题
联合动量对比聚类
Federated Momentum Contrastive Clustering
论文作者
论文摘要
我们提出了联合动量对比聚类（FEDMCC），这是一个学习框架，不仅可以在分布式本地数据上提取歧视性表示，而且可以执行数据群集。在FEDMCC中，转换的数据对通过在线和目标网络都通过，从而确定了四个表示损失的表示。 FEDMCC生成的由此产生的高质量表示可以胜过几种现有的自我监督学习方法，用于线性评估和半监督学习任务。 FEDMCC可以通过我们称为动量的对比聚类（MCC）轻松地适应普通的集中式聚类。我们表明，MCC可以在某些数据集（例如STL-10和Imagenet-10）中实现最先进的聚类精度。我们还提出了一种减少聚类方案的内存足迹的方法。
We present federated momentum contrastive clustering (FedMCC), a learning framework that can not only extract discriminative representations over distributed local data but also perform data clustering. In FedMCC, a transformed data pair passes through both the online and target networks, resulting in four representations over which the losses are determined. The resulting high-quality representations generated by FedMCC can outperform several existing self-supervised learning methods for linear evaluation and semi-supervised learning tasks. FedMCC can easily be adapted to ordinary centralized clustering through what we call momentum contrastive clustering (MCC). We show that MCC achieves state-of-the-art clustering accuracy results in certain datasets such as STL-10 and ImageNet-10. We also present a method to reduce the memory footprint of our clustering schemes.
