Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning. While methods utilizing sparsification or others can largely lower the communication overhead, the convergence rate is also greatly compromised. In this paper, we propose a novel method, named single-step synthetic features compressor (3SFC), to achieve communication-efficient FL by directly constructing a tiny synthetic dataset based on raw gradients. Thus, 3SFC can achieve an extremely low compression rate when the constructed dataset contains only one data sample. Moreover, 3SFC's compressing phase utilizes a similarity-based objective function so that it can be optimized with just one step, thereby considerably improving its performance and robustness. In addition, to minimize the compressing error, error feedback (EF) is also incorporated into 3SFC. Experiments on multiple datasets and models suggest that 3SFC owns significantly better convergence rates compared to competing methods with lower compression rates (up to 0.02%). Furthermore, ablation studies and visualizations show that 3SFC can carry more information than competing methods for every communication round, further validating its effectiveness.
翻译:减少联邦学习(FL)中的通信开销对于大型分布式隐私保护机器学习而言具有挑战性但至关重要。虽然利用稀疏化或其他方法可以大大降低通信开销,但收敛速度也大大降低。为此,本文提出了一种名为“单步合成特征压缩器”(3SFC)的新方法,以在原始梯度基础上直接构建微小的合成数据集,从而实现高效的FL。因此,当构建的数据集仅包含一个数据样本时,3SFC可以实现极低的压缩率。此外,3SFC的压缩阶段利用基于相似性的目标函数,因此可以在一步操作中进行优化,从而大大提高其性能和稳健性。此外,为了最大程度地减小压缩误差,3SFC还将误差反馈(EF)纳入其中。多个数据集和模型上的实验表明,3SFC相对于压缩率更低的竞争方法具有显着更好的收敛速度(高达0.02%的压缩率)。此外,削减研究和可视化显示,相对于竞争方法,3SFC每个通信回合可以传递更多信息,进一步验证了其有效性。