To accelerate the convergence speed and improve the accuracy of the federated shared model, this paper proposes a Federated Transfer Learning method based on frozen network parameters. The article sets up frozen two, three, and four layers network parameters, 8 sets of experimental tasks, and two target users for comparative experiments on frozen network parameters, and uses homomorphic encryption based Federated Transfer Learning to achieve secret transfer of parameters, and the accuracy, convergence speed, and loss function values of the experiment were compared and analyzed. The experiment proved that the frozen three-layer network parameter model has the highest accuracy, with the average values of the two target users being 0.9165 and 0.9164; The convergence speed is also the most ideal, with fast convergence completed after 25 iterations. The training time for the two users is also the shortest, with 1732.0s and 1787.3s, respectively; The loss function value shows that the lowest value for User-II is 0.181, while User-III is 0.2061. Finally, the unlabeled and non-empty enterprise credit data is predicted, with 61.08% of users being low-risk users. This article achieves rapid convergence of the target network model by freezing source domain network parameters in a shared network, saving computational resources.

中文翻译：

---

基于联邦迁移学习冻结网络参数的小微企业信用风险预测


为了加快联邦共享模型的收敛速度，提高其准确性，该文提出了一种基于冻结网络参数的联邦迁移学习方法。本文设置了冻结的二、三、四层网络参数，8组实验任务，以及2个目标用户，对冻结网络参数进行了对比实验，并使用基于同态加密的联邦迁移学习实现参数的秘密传递，并对实验的准确率、收敛速度和损失函数值进行了对比分析。实验证明，冻结的三层网络参数模型精度最高，两个目标用户的平均值分别为 0.9165 和 0.9164;收敛速度也是最理想的，25 次迭代后即可完成快速收敛。两个用户的训练时间也是最短的，分别为 1732.0 秒和 1787.3 秒;损失函数值显示用户 II 的最低值为 0.181，而用户 III 为 0.2061。最后，预测未标注和非空的企业信用数据，其中 61.08% 的用户为低风险用户。该文通过将源域网络参数冻结在共享网络中，节省了计算资源，实现了目标网络模型的快速收敛。