[go: up one dir, main page]
Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Individual(personalized) hyper-parameters for federated learning #2582

Open
darpitdavetamu opened this issue Feb 28, 2022 · 0 comments
Open

Individual(personalized) hyper-parameters for federated learning #2582

darpitdavetamu opened this issue Feb 28, 2022 · 0 comments
Labels
enhancement New feature or request

Comments

@darpitdavetamu
Copy link
darpitdavetamu commented Feb 28, 2022 •
edited

My custom-loss function

def custom_loss(keras.losses.loss):

  loss_1 = K.mean(K.square((self.y_pred - self.y_true)/self.y_true))

  loss_2 = K.mean(K.square(self.y_pred - self.y_true))

  final_loss = \alpha * loss_1 + (1 - alpha) * loss_2


  return final_loss

Can I pass different alpha (hyperparameter) for individual users in tensorflow_federated?
@darpitdavetamu darpitdavetamu added the enhancement New feature or request label Feb 28, 2022
@darpitdavetamu darpitdavetamu changed the title Individual paramters for federated learning Individual hyper-parameters for federated learning Feb 28, 2022
@darpitdavetamu darpitdavetamu changed the title Individual hyper-parameters for federated learning Individual(personalized) hyper-parameters for federated learning Feb 28, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@darpitdavetamu