Chuizheng Meng

icon indicating a website link https://mengcz13.github.io/ icon indicating an email [email protected]

icon company University of Southern California icon location Los Angeles

Results 2 issues of Chuizheng Meng

Wrong loss function?

1 comment

I notice that the code uses CrossEntropyLoss for local training: https://github.com/pliang279/LG-FedAvg/blob/7af0568b2cae88922ebeacc021b1679815092f4e/models/Update.py#L28 And it accepts the log-probabilities as input: https://github.com/pliang279/LG-FedAvg/blob/7af0568b2cae88922ebeacc021b1679815092f4e/models/Update.py#L50 The output of CNN networks is also logsoftmax: https://github.com/pliang279/LG-FedAvg/blob/7af0568b2cae88922ebeacc021b1679815092f4e/models/Nets.py#L104 But according...

Question about the current implementation of mobility regularity-aware loss

https://github.com/FIBLAB/MoveSim/blob/93e6837fa318a9e5a3966f5267accfb303ed8bb6/code/main.py#L165 Is the current implementation of mobility regularity-aware loss correct? Now both $L_d$ and $L_p$ are directly added to the loss for calculating policy gradient, but they won't produce any...