动态调整模型结构，让不同设备高效协作训练
FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures
- 训练时动态调整模型结构以适配异构设备
- 相比现有方法最高提升23.30%准确率
- 适合设备能力差异大的真实场景使用
传统联邦学习在异构环境下面临效率与准确率的挑战，客户端采用不同模型架构且计算资源各异，导致聚合过程复杂，性能受限且泛化能力下降。为此，我们提出FedADP，一种通过在聚合过程中动态调整模型架构来适应客户端异构性的联邦学习框架。该框架可有效促进能力各异客户端间的协作，最大化资源利用率并保障模型质量。实验表明，FedADP显著优于现有方法（如FlexiFed），在异构真实场景下最高实现23.30%的准确率提升，增强了模型适应性与训练效率。
原文摘要 · Abstract (English)
Traditional Federated Learning (FL) faces significant challenges in terms of efficiency and accuracy, particularly in heterogeneous environments where clients employ diverse model architectures and have varying computational resources. Such heterogeneity complicates the aggregation process, leading to performance bottlenecks and reduced model generalizability. To address these issues, we propose FedADP, a federated learning framework designed to adapt to client heterogeneity by dynamically adjusting model architectures during aggregation. FedADP enables effective collaboration among clients with differing capabilities, maximizing resource utilization and ensuring model quality. Our experimental results demonstrate that FedADP significantly outperforms existing methods, such as FlexiFed, achieving an accuracy improvement of up to 23.30%, thereby enhancing model adaptability and training efficiency in heterogeneous real-world settings.
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。