< Back to Article

FedEmoNet: Privacy-preserving federated learning with TCN-Transformer fusion for cross-corpus speech emotion recognition

Fig 14

Federated learning training dynamics.

(a) Global accuracy convergence; (b) Loss on logarithmic scale; (c) Per-client heterogeneous convergence; (d) FedProx vs FedAvg comparison.

doi: https://doi.org/10.1371/journal.pone.0342953.g014