Hardware-Aware Federated Learning for Speech Emotion Recognition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911713621704704 |
|---|---|
| author | Yuksel, Beyazit Bestami Dikbiyik, Emrah |
| author_facet | Yuksel, Beyazit Bestami Dikbiyik, Emrah |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24712 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hardware-Aware Federated Learning for Speech Emotion Recognition Yuksel, Beyazit Bestami Dikbiyik, Emrah Machine Learning Human-Computer Interaction 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%. |
| title | Hardware-Aware Federated Learning for Speech Emotion Recognition |
| topic | Machine Learning Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.24712 |