提出联邦学习消息的分类体系，涵盖模型结构、统计摘要与数据表征。
Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages
- 按信息类型将联邦消息分为三类：模型结构、统计摘要、数据条件表示
- 202篇近年论文显示2021年后消息形式显著多样化
- 为不同硬件与安全需求提供优化路径，适合系统设计者参考
联邦学习正从传统模型权重和梯度交换演进，但现有定义无法涵盖合成数据和联邦分析等新型信息。本文提出一个形式化数学定义，涵盖效用与隐私双重考量。构建三类消息分类：模型结构、统计摘要、数据条件表示。基于计算开销、通信成本和隐私风险评估各类型，揭示去中心化训练中的权衡。对202篇近期论文的分析表明，自2021年起消息范式显著多样化，标志着从标准深度学习更新向更专业信息共享的转变。该框架为未来研究在不同软硬件与安全要求下优化联邦系统提供结构化路径。
原文摘要 · Abstract (English)
Federated Learning is rapidly evolving beyond the exchange of traditional model weights and gradients, yet existing definitions fail to capture the full scope of modern payloads like synthetic data and federated analytics. This paper addresses the gap by proposing a formal mathematical definition of a federated message that accounts for both utility and privacy. We introduce a taxonomy that organizes these exchanges into three categories: model structures, statistical summaries, and data-conditioned representations. By evaluating these groups based on computational demands, communication costs, and privacy risks, we provide a clearer understanding of the trade-offs involved in decentralized training. Our review of 202 recent publications highlights a significant shift since 2021 toward diverse messaging paradigms, signaling a move away from standard deep learning updates toward more specialized information sharing. This framework provides a structured path for future research to optimize federated systems for varying hardware and security requirements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。