With the rapid growth of big data, extracting meaningful knowledge from data is crucial for machine learning. The existing Swarm Learning data collaboration models face challenges such as data security, model security, high communication overhead, and model performance optimization. To address this, we propose the Swarm Mutual Learning (SML). Firstly, we introduce an Adaptive Mutual Distillation Algorithm that dynamically controls the learning intensity based on distillation weights and strength, enhancing the efficiency of knowledge extraction and transfer during mutual distillation. Secondly, we design a Global Parameter Aggregation Algorithm based on homomorphic encryption, coupled with a Dynamic Gradient Decomposition Algorithm using singular value decomposition. This allows the model to aggregate parameters in ciphertext, significantly reducing communication overhead during uploads and downloads. Finally, we validate the proposed methods on real datasets, demonstrating their effectiveness and efficiency in model updates. On the MNIST dataset and CIFAR-10 dataset, the local model accuracies reached 95.02% and 55.26%, respectively, surpassing those of the comparative models. Furthermore, while ensuring the security of the aggregation process, we significantly reduced the communication overhead for uploading and downloading.

随着大数据的快速增长，从数据中提取有意义的知识对于机器学习至关重要。现有的Swarm Learning数据协作模型面临数据安全、模型安全、通信开销高、模型性能优化等挑战。为了解决这个问题，我们提出了群体相互学习（SML）。首先，我们引入了一种自适应相互蒸馏算法，该算法根据蒸馏权重和强度动态控制学习强度，提高相互蒸馏过程中知识提取和迁移的效率。其次，我们设计了一种基于同态加密的全局参数聚合算法，结合使用奇异值分解的动态梯度分解算法。这允许模型以密文形式聚合参数，从而显着减少上传和下载期间的通信开销。最后，我们在真实数据集上验证了所提出的方法，证明了它们在模型更新中的有效性和效率。在MNIST数据集和CIFAR-10数据集上，局部模型准确率分别达到95.02%和55.26%，超过了对比模型。此外，在保证聚合过程安全的同时，我们显着降低了上传和下载的通信开销。