一跳式联邦学习，用生成数据提升模型性能。
Federated Gaussian Mixture Models
- 本地训练GMM后，单轮通信聚合生成合成数据。
- 性能媲美非联邦方法，异常检测表现稳健。
- 适合边缘计算，降低通信开销，灵活适配设备。
本文提出FedGenGMM，一种针对无监督学习场景的新型单次通信联邦学习方法，用于高斯混合模型（GMM）。在联邦学习中，多个分布式客户端协作训练模型而无需共享原始数据，面临统计异质性、高通信成本和隐私问题。FedGenGMM通过单轮通信聚合本地独立训练的GMM模型，利用GMM的生成特性，在服务器端生成合成数据以高效训练全局模型。在涵盖图像、表格和时间序列数据的多种数据集上评估表明，即使在显著数据异质性下，FedGenGMM性能仍可媲美非联邦及迭代联邦方法。此外，该方法显著降低通信开销，在异常检测任务中保持鲁棒性能，并支持本地模型复杂度的灵活性，特别适用于边缘计算环境。
原文摘要 · Abstract (English)
This paper introduces FedGenGMM, a novel one-shot federated learning approach for Gaussian Mixture Models (GMM) tailored for unsupervised learning scenarios. In federated learning (FL), where multiple decentralized clients collaboratively train models without sharing raw data, significant challenges include statistical heterogeneity, high communication costs, and privacy concerns. FedGenGMM addresses these issues by allowing local GMM models, trained independently on client devices, to be aggregated through a single communication round. This approach leverages the generative property of GMMs, enabling the creation of a synthetic dataset on the server side to train a global model efficiently. Evaluation across diverse datasets covering image, tabular, and time series data demonstrates that FedGenGMM consistently achieves performance comparable to non-federated and iterative federated methods, even under significant data heterogeneity. Additionally, FedGenGMM significantly reduces communication overhead, maintains robust performance in anomaly detection tasks, and offers flexibility in local model complexities, making it particularly suitable for edge computing environments.
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。