用相关性合并相似模型，提升异构数据下联邦学习的稳定性和效率
A Novel Pearson Correlation-Based Merging Algorithm for Robust Distributed Machine Learning with Heterogeneous Data
- 基于皮尔逊相关系数筛选相似本地模型进行聚合
- 10轮训练后在三种场景下准确率分别达0.82、0.73、0.66
- 适合应对数据异构、网络波动和恶意攻击的联邦学习场景
联邦学习在数据分布异构及网络条件恶劣（如延迟、丢包、数据投毒攻击）时面临挑战。本文提出一种基于SCAFFOLD算法的新方法，通过皮尔逊相关系数衡量本地模型相似性，将高相似度模型合并为中间节点，减少本地节点数量，从而降低通信开销并提升全局模型鲁棒性。在模拟联邦学习环境下对MNIST数据集进行实验，使用CNN模型训练10轮后，该方法在正常、丢包和数据投毒攻击场景下的准确率分别为0.82、0.73和0.66，优于基线SCAFFOLD算法，验证了其在效率与抗干扰能力上的优势。
原文摘要 · Abstract (English)
Federated learning faces significant challenges in scenarios with heterogeneous data distributions and adverse network conditions, such as delays, packet loss, and data poisoning attacks. This paper proposes a novel method based on the SCAFFOLD algorithm to improve the quality of local updates and enhance the robustness of the global model. The key idea is to form intermediary nodes by merging local models with high similarity, using the Pearson correlation coefficient as a similarity measure. The proposed merging algorithm reduces the number of local nodes while maintaining the accuracy of the global model, effectively addressing communication overhead and bandwidth consumption. Experimental results on the MNIST dataset under simulated federated learning scenarios demonstrate the method's effectiveness. After 10 rounds of training using a CNN model, the proposed approach achieved accuracies of 0.82, 0.73, and 0.66 under normal conditions, packet loss and data poisoning attacks, respectively, outperforming the baseline SCAFFOLD algorithm. These results highlight the potential of the proposed method to improve efficiency and resilience in federated learning systems.
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。