Federated Learning (FL) enables collaborative optimization of machine learning models across decentralized data by aggregating model parameters. Our approach extends this concept by aggregating "knowledge" derived from models, instead of model parameters. We present a novel framework called CoDream, where clients collaboratively optimize randomly initialized data using federated optimization in the input data space, similar to how randomly initialized model parameters are optimized in FL. Our key insight is that jointly optimizing this data can effectively capture the properties of the global data distribution. Sharing knowledge in data space offers numerous benefits: (1) model-agnostic collaborative learning, i.e., different clients can have different model architectures; (2) communication that is independent of the model size, eliminating scalability concerns with model parameters; (3) compatibility with secure aggregation, thus preserving the privacy benefits of federated learning; (4) allowing of adaptive optimization of knowledge shared for personalized learning. We empirically validate CoDream on standard FL tasks, demonstrating competitive performance despite not sharing model parameters. Our code: https://mitmedialab.github.io/codream.github.io/

翻译：联邦学习通过聚合模型参数，实现了跨分散数据的机器学习模型协同优化。本文提出的方法通过聚合模型导出的"知识"而非模型参数，拓展了这一概念。我们提出了名为CoDream的新型框架：在该框架中，各客户端在输入数据空间内采用联邦优化方式，协同优化随机初始化的数据，这与联邦学习中随机初始化模型参数的优化方式类似。我们的核心洞察在于：联合优化这些数据能有效捕获全局数据分布的特性。基于数据空间的知识共享具有多重优势：(1) 实现模型无关的协同学习，即不同客户端可使用各异构模型架构；(2) 通信量与模型规模无关，消除了模型参数的扩展性问题；(3) 兼容安全聚合，从而保持联邦学习的隐私保护优势；(4) 支持对共享知识进行自适应优化以促进个性化学习。我们在标准联邦学习任务上对CoDream进行了实证验证，结果表明尽管未共享模型参数，该方法仍展现出具有竞争力的性能。代码地址：https://mitmedialab.github.io/codream.github.io/