Stack Overflow
Stack Overflow

Questions tagged [federated-learning]

167 questions
0
votes
0 answers

Train Keras model after Split for federated learning

Hi i am trying to train the keras model after split. simulating the keras model are placed on different devices and each device have their weights. that devices passes their intermediate output to host and host device receive intermediate output and…
parmpal singh gill
  • 1
0
votes
1 answer

Local dataset in Federated learning: client side, is the local update performed on a different subset of the local dataset each round?

I was wondering if in a Federated Learning approach I need to split the local dataset in a number of batches equal to the number of communication rounds. Otherwise I need to update locally on the whole local dataset each round. Building a federated…
Novak
  • 1
0
votes
0 answers

Federated Learning and onboard training using Raspberry Pi Pico RP2040 and Tensorflow

I am trying to implement federated learning in a group of raspberry pi picos. I had the following queries: What would be the best means for performing onboard ML training on the Raspberry Pi Pico, using real-time sensor data? I was wondering…
user21113337
  • 1
0
votes
0 answers

Transferring models between two PCs via PostgresSQL database

I have two PCs that want to share tensorflow models "hdf5 format" in a federated learning manner via a PostgresSQL database. The models will be trained locally on both machines, and then transferred to the database along with the training history.…
Mr. Gulliver
  • 1
  • 1
0
votes
0 answers

How to resolve "module has no attribute 'entropy_decode_index' error in ubuntu for TFF?

I got "module '0b1a516c7ccf3157373118bcf0f434168745c8a4' has no attribute 'entropy_decode_index' error after a clean intall of tensorflow federated (TFF) on Ubuntu 22.04. System: AMD 6900HS, Nvidia3050ti. The first "import tensorflow_federated" line…
Egemen Isguder
  • 1
  • 1
0
votes
0 answers

How to measure time of training for one node with tensorflow federated?

i want to benchmark different federated learning tools, does anyone know how to measure the training time with tensorflow federated? In all the tutorials the trainer only does the next function to perform training on all nodes and aggregating and i…
werwom
  • 1
0
votes
0 answers

Federated Learning - Why does Global Model goes to 10k+?

I am currently working on a Personalized Federated Learning Project. Everything has been going well. I am getting around 95% of average local model accuracy and 93% for global model on a binary classification task. In addition, recall and precision…
Ki Riven
  • 33
  • 4
0
votes
0 answers

Federated Learning Local Clients Flucuating Accuracies

I am currently working on a personalized federated learning research. The current simulation structure is as follows: Global model with with 5 global rounds Local model with 10 clients and 4 local rounds Model is CNN for 11 classes…
Ki Riven
  • 33
  • 4
0
votes
0 answers

Flower running the server and clients on different machines

I use Flower API for federated learning applications. Is there any way to run the server and clients on different machines for a real-world benchmark?
Mastour Ikhlass
  • 99
  • 1
  • 1
  • 7
0
votes
0 answers

Cannot install and import tensorflow_federated in colab

I want to try a simple federated learning example in python. For it, I need to import tensorflow_federated package. import tensorflow_federated as tff Here is the stack trace TypeError Traceback (most recent call…
HoOman
  • 455
  • 1
  • 7
  • 15
0
votes
0 answers

hyperparameter tuning with cross validation in federated learning

i want to implement the federated learning framework. for finding a set of optimal hyperparameter values, How should I implement cross-validation procedure? Should I train a traditional machine learning model or Federated learning process? please…
Afsane
  • 1
0
votes
1 answer

AttributeError: 'Model' object has no attribute '_backward_hooks'

Trying to implement the reaserch paper: https://ieeexplore.ieee.org/document/9479786/ Training a Monotone Network with architechture: class Model(nn.Module): def __init__(self, q, s): self.layer_s_list = [nn.Linear(5, s) for _ in range(q)] …
Geeky Coder
  • 1
  • 2
0
votes
1 answer

Federated learning weighted aggregation

I would like to add different weights to clients in Federated learning, so in the aggregation stage, each client has a different impact on the global model. For example: Client_1 has 2X impact Client_2 has X impact I am looking for suggestions to…
shadow
  • 53
  • 1
  • 7
0
votes
0 answers

Multi-GPU TFF simulation

When running my custom federated learning code on GPU (using tff.templates.IterativeProcess): I am getting following warning: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2022-11-12 12:22:28.981770: I…
Deepali Kushwaha
  • 1
  • 1
0
votes
0 answers

Why we should discuss the convergence analysis?

In my research and learning of Federated Learning, I noticed that most of the researchers are discussing the convergence rates of the models. Why is that so important and how it can benefit the model discussion? and if the model fast converged in…
Eden
  • 325
  • 3
  • 13
1 2 3
…
11 12