针对语音情感识别，提出硬件感知的联邦学习框架，提升训练效率。
Hardware-Aware Federated Learning for Speech Emotion Recognition
- 根据设备性能动态选客户端并调整本地训练轮数
- 50轮内准确率达0.352，训练时间减少36.5%
- 适合资源异构的边缘设备部署
联邦学习（FL）支持在分布式边缘设备间实现隐私保护的协同训练，但实际部署中客户端硬件差异大，导致训练轮次延长、系统开销上升。本文针对会话划分的IEMOCAP数据集，提出一种硬件感知的联邦学习框架，集成硬件性能检测、Top-K客户端选择与自适应本地训练轮数，在统一训练流程中实现优化。在非独立同分布设置下，与FedAvg、FedProx及随机Top-K选择方法对比，本方法在50轮联邦训练与5次独立实验中，验证准确率达到0.352，总训练时间相比FedAvg降低约36.5%，累计通信成本减少40%。
原文摘要 · Abstract (English)
Federated learning (FL) enables privacy-preserving collaborative training across distributed edge devices, but real deployments involve heterogeneous clients with different processing power, memory capacity, and communication latency, which often increase round duration and system cost. This paper proposes a hardware-aware federated learning framework for emotion recognition on session-partitioned IEMOCAP that integrates hardware profiling, top-K client selection, and adaptive local epochs within a unified training loop. We compare the method against FedAvg, FedProx, and random top-K selection under a non-IID setup and show that, across 50 federated rounds and 5 independent trials, the proposed approach achieves competitive validation accuracy (0.352), reduces total training time by about 36.5% compared to FedAvg, and lowers cumulative communication cost by 40%.
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。