论文标题
深网的分散自适应聚类对客户协作有益
Decentralized adaptive clustering of deep nets is beneficial for client collaboration
论文作者
论文摘要
我们研究了在分散的点对点环境中培训个性化深度学习模型的问题，重点是客户之间的数据分布在客户之间有所不同，而不同的客户具有不同的本地学习任务。 We study both covariate and label shift, and our contribution is an algorithm which for each client finds beneficial collaborations based on a similarity estimate for the local task.我们的方法不依赖于难以估计的超参数，例如客户群的数量，而是使用基于新颖的自适应八卦算法的软群集分配不断适应网络拓扑。我们在各种环境中测试了所提出的方法，在各种环境中，数据不是独立的，并且在客户端之间分布相同。实验评估表明，对于此问题设置，所提出的方法的性能优于以前的最新算法，并且在以前的方法失败的情况下处理情况很好。
We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks. We study both covariate and label shift, and our contribution is an algorithm which for each client finds beneficial collaborations based on a similarity estimate for the local task. Our method does not rely on hyperparameters which are hard to estimate, such as the number of client clusters, but rather continuously adapts to the network topology using soft cluster assignment based on a novel adaptive gossip algorithm. We test the proposed method in various settings where data is not independent and identically distributed among the clients. The experimental evaluation shows that the proposed method performs better than previous state-of-the-art algorithms for this problem setting, and handles situations well where previous methods fail.
