跨模型架构协作学习，通信量少且保护隐私。
Communication-Efficient and Interoperable Distributed Learning
- 统一融合层输出维度，实现异构模型互通。
- 仅交换融合层输出，通信量低于传统方法。
- 适合隐私敏感的分布式训练场景。
跨异构模型架构的协同学习面临互操作性与隐私保护的双重挑战。本文提出一种通信高效的分布式学习框架，支持模型异构性，并在推理时实现模块化组合。为确保互操作性，所有客户端采用统一的融合层输出维度，使每个模型可拆分为个性化基础模块与通用模块。客户端仅共享融合层输出，模型参数与结构保持私密。实验表明，该框架在通信效率上优于联邦学习（FL）和联邦分割学习（FSL）基线，同时在异构架构下维持稳定的训练性能。
原文摘要 · Abstract (English)
Collaborative learning across heterogeneous model architectures presents significant challenges in ensuring interoperability and preserving privacy. We propose a communication-efficient distributed learning framework that supports model heterogeneity and enables modular composition during inference. To facilitate interoperability, all clients adopt a common fusion-layer output dimension, which permits each model to be partitioned into a personalized base block and a generalized modular block. Clients share their fusion-layer outputs, keeping model parameters and architectures private. Experimental results demonstrate that the framework achieves superior communication efficiency compared to federated learning (FL) and federated split learning (FSL) baselines, while ensuring stable training performance across heterogeneous architectures.
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。