Could you support knowledge distillation-based FL algorithms like FedED, Fedmd, or FedDF

Currently, your platform supports some parameter-average-based FL algorithms. Could you support knowledge-distillation-based FL algorithms like FedED, Fedmd, or FedDF?

[FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction](https://aclanthology.org/2020.emnlp-main.165.pdf),
[Fedmd: Heterogenous federated learning via model distillation. NeurIPS workshop, 2019](https://arxiv.org/pdf/1910.03581.pdf )
FedDF, [Ensemble distillation for robust model fusion in federated learning. NeurIPS, 2020](https://arxiv.org/pdf/2006.07242.pdf)