| Virual Oral Presentation Slide by Slide |
IEEE/ICACT20260326 Slide.04
[Big Slide]
| Oral Presentation |
|
|
Slide 4. Our contributions are summarized as follows: 1. FSANL, a single-stage federated framework that is robust to non-IID distributions and client-level heterogeneous label noise. 2. FSANL introduces a unified loss function combining symmetric and active negative loss components with L1- based global model regularization. 3. Extensive experiments on CIFAR-10 demonstrate the effectiveness and scalability of FSANL compared to state-of-the-art baselines. | |
| [Go to Next Slide] |