GAL：分散式多组织协作的梯度辅助学习
GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations
摘要：
多个组织之间的协作，如金融机构、医疗中心和分散环境中的零售市场，对于提供更好的服务和性能至关重要。然而，底层组织可能对共享其本地数据、模型和目标函数不感兴趣。这些要求为多组织协作带来了新的挑战。在这项工作中，我们提出了梯度辅助学习（GAL），多个组织在监督学习任务中相互帮助的新方法，而无需共享本地数据，模型和目标函数。在这个框架中，所有参与者协作优化局部损失函数的集合，每个参与者通过迭代拟合总体目标函数的梯度来自主构建自己的模型。我们还提供了GAL的渐近收敛性分析和实际案例研究。实验研究表明，当所有数据、模型和目标函数都完全公开时，GAL可以实现接近集中式学习的性能。
英文摘要：
Collaborations among multiple organizations, such as financial institutions, medical centers, and retail markets in decentralized settings are crucial to providing improved service and performance. However, the underlying organizations may have little interest in sharing their local data, models, and objective functions. These requirements have created new challenges for multi-organization collaboration. In this work, we propose Gradient Assisted Learning (GAL), a new method for multiple organizations to assist each other in supervised learning tasks without sharing local data, models, and objective functions. In this framework, all participants collaboratively optimize the aggregate of local loss functions, and each participant autonomously builds its own model by iteratively fitting the gradients of the overarching objective function. We also provide asymptotic convergence analysis and practical case studies of GAL. Experimental studies demonstrate that GAL can achieve performance close to centralized learning when all data, models, and objective functions are fully disclosed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
