论文标题
部分可观测时空混沌系统的无模型预测
Bayesian Federated Neural Matching that Completes Full Information
论文作者
论文摘要
联合学习是一种现代的机器学习范式，在该范式中，本地训练的模型被蒸馏成全球模型。由于神经网络的固有置换不变性，概率联合神经匹配（PFNM）在局部神经元的生成过程中采用了贝叶斯非参数框架，然后在每个替代优化迭代中创建线性总和分配。但是根据我们的理论分析，PFNM中的优化迭代省略了现有的全球信息。在这项研究中，我们提出了一种新颖的方法，该方法通过在每次迭代中引入Kullback-Leibler Divergence惩罚来克服这种缺陷。通过对图像分类和语义分割任务进行实验证明了我们方法的有效性。
Federated learning is a contemporary machine learning paradigm where locally trained models are distilled into a global model. Due to the intrinsic permutation invariance of neural networks, Probabilistic Federated Neural Matching (PFNM) employs a Bayesian nonparametric framework in the generation process of local neurons, and then creates a linear sum assignment formulation in each alternative optimization iteration. But according to our theoretical analysis, the optimization iteration in PFNM omits global information from existing. In this study, we propose a novel approach that overcomes this flaw by introducing a Kullback-Leibler divergence penalty at each iteration. The effectiveness of our approach is demonstrated by experiments on both image classification and semantic segmentation tasks.
