ericboniface

Results 23 comments of ericboniface

Elaborate a test scenario coherent with fertility context

@celinejacques I am recycling this issue and linking it to your PyTorch PR!

Elaborate a test scenario coherent with fertility context

Hi guys @celinejacques @jeromechambost , doing some sorting in the old issues - is this one still of interest to you, and realistic?

Study Federated learning litterature and libraries

@jeromechambost this seems to be the perfect issue for you to update with your research 😄

Study Federated learning litterature and libraries

@jeromechambost it would be interesting to complete the bibliography file @HeytemBou and @arthurPignet initiated in PR #348

make the library label agnostic

Is this still relevant @arthurPignet ?

Add parameter : fraction of partners used at each federated round

@HeytemBou I think you are introducing this in your DRFA PR right?

Add parameter : fraction of partners used at each federated round

The attribute has been added by @HeytemBou in PR #354 (as a `Scenario()` attribute), but it remains to adapt standard multi-partner learning approaches to leverage it.

Add parameter : fraction of partners used at each federated round

@arthurPignet indicates that there is a similar mechanism in PVRL - to be checked, see if some can be reused and/or upgraded when we implement this fraction of partners approach....

What happens when we clip batch_size ?

- [ ] Update `MAX_BATCH_SIZE` (value to be determined) - [ ] Add a log when the clipping is triggered (log leve `INFO`)

Profile timing for minibatch federated learning

@RomainGoussault do you think it would be interesting to profile again as you did above?