What's the meaning of last_weight_accumulator?

ebagdasa / backdoor_federated_learning

Source code for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)

MIT License

273 stars 65 forks source link

Closed pangjieyu closed 3 years ago

pangjieyu commented 3 years ago

I noticed that the last_weight_accumulator in the train function is not used. Will this cause the network training speed to drop?

ebagdasa commented 3 years ago

you can ignore it, it was for some older experiments.