My DQN implementation based on flsim

[tian1327]

Hi there,

Thanks for the good work! Just a question, is the DQN model trained (by selecting 1 participating device as mentioned in the paper) before being deployed to the server for FL communications? Or does it trained in parallel with the FL communications? If so, how? Because in FL communications you are using DQN to select top k devices for training right?

Anyone else can help me understand this? Thanks!

[tian1327]

Hi, I would like to share my implementation of DQN with everyone who is interested. I successfully reproduced the baselines like FedAvg, K-means, K-clusters, and PCA for state compression. However, my DQN implementation cannot reproduce the same training performance as shown in the paper.

Anyone interested in this topic is welcome to work on top of my implementation.

You can find my implementation, short presentation, slides, and report here. https://github.com/tian1327/flsim_dqn

Thanks