is formulating a robust, efficient training scheme with extensive results and analysis which is significant enough. "

We thank all reviewers for their time and their valuable feedback. We will add corrections/clarifications as suggested. We would like to emphasize our contribution, as summarized by R5's thorough review: "What's novel about this paper Our proposed FedDF is not the mentioned engineering solution. FL round; thus mutual beneficial information can be shared across architectures . GAN training is not involved in all stages of FL and cannot steal clients' Data generation is done by the (frozen) generator before the FL training by performing inference on random noise.