隐私保护八卦学习
Privacy Preserving Gossip Learning
浏览论文内容
中文总结 AI 辅助
提出一种去中心化隐私保护学习算法，基于无遗忘调参和私有推-求和八卦协议，实现样本顺序学习中的隐私保护与几何收敛。
中文摘要 AI 辅助
我们提出了一种去中心化的隐私保护学习算法，其中每个智能体持有一个私有样本和一个共享模型。样本按顺序学习，每次更新必须保持先前学习样本处的端点映射，同时保护私有数据。这赋予每个智能体三个角色：（i）学习者，更新模型参数；（ii）教师，其样本在当前迭代中被学习；（iii）受保护智能体，其样本已被学习。我们基于“无遗忘调参”（TwF）方法保留先前学习的映射，并证明当受保护智能体集合包含另一个具有相同标签的样本时，TwF为学习者提供不可区分性保证。对于教师，我们构建了一个极小极大最优控制问题，将差分隐私噪声建模为最坏情况扰动，以防止性能损失，同时保持梯度的相同隐私水平。对于受保护智能体，我们在本地计算投影，并使用私有推-求和八卦协议进行聚合。我们证明了去中心化八卦算法和TwF分布式投影的几何收敛性。
英文摘要
We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learned sequentially, and each update must preserve the endpoint mappings at previously learned samples while protecting private data. This gives each agent three roles: (i) a learner that updates the model parameters, (ii) a teacher whose sample is learned at the current iteration, and (iii) a protected agent whose sample has already been learned. We build on Tuning without Forgetting (TwF) method to preserve previously learned mappings and show that TwF provides an indistinguishability guarantee for the learner whenever the set of protected agents contains another sample with the same label. For the teacher, we formulate a minimax optimal control problem that models the differential privacy noise as a worst-case disturbance to prevent performance loss while maintaining the same level of privacy for the gradient. For the protected agents, we compute the projections locally and aggregate them using a private push-sum gossip protocol. We prove geometric convergence of the decentralized gossip algorithm and of the distributed projection for TwF.
发表机构
- University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。
