Stack Overflow
Stack Overflow

Questions tagged [federated-learning]

167 questions
6
votes
3 answers

How to create federated dataset from a CSV file?

I have selected this dataset: https://www.kaggle.com/karangadiya/fifa19 Now, I would like to convert this CSV file into the federated dataset to fit in the model. Tensorflow provided tutorials on federated learning where they have used a pre-defined…
Mahedi Hasan Jisan
  • 89
  • 1
  • 6
4
votes
1 answer

How to load Fashion MNIST dataset in Tensorflow Fedarated?

I am working on a project with Tensorflow federated. I have managed to use the libraries provided by TensorFlow Federated Learning simulations in order to load, train, and test some datasets. For example, i load the emnist dataset emnist_train,…
Panagiotis Drakatos
  • 2,851
  • 4
  • 31
  • 43
4
votes
1 answer

Implement data generator in federated training

(I have posted the question on https://github.com/tensorflow/federated/issues/793 and maybe also here!) I have customized my own data and model to federated interfaces and the training converged. But I am confused about an issue that in an images…
miaoz18
  • 41
  • 2
3
votes
1 answer

How to tune hyper parameters for CIFAR100 in tensorflow_federated TFF without dropping in the accuracy?

I'm trying to test this tutorial https://www.tensorflow.org/federated/tutorials/tff_for_federated_learning_research_compression with CIFAR100 dataset, but the accuracy is dropping each round! Does my tuning for the hyper parameter is the…
user18969005
  • 87
  • 6
3
votes
1 answer

How to build federated learning model of unbalanced and small dataset

I am working to build a federated learning model using TFF and I have some questions: I am preparing the dataset, I have separate files of data, with same features and different samples. I would consider each of these files as a single client. How…
Eden
  • 325
  • 3
  • 13
3
votes
1 answer

Federated Averaging and TensorFlow

I am a newbie in federated learning and just getting to know TensorFlow Federated TFF framework. I have some questions in my mind I would be really appreciated it if anybody can clarify them: Does Federated Averaging algorithm the only aggregation…
Reem
  • 79
  • 6
3
votes
2 answers

TFF : test accuracy fluctuate

I train a ResNet50 model with TFF, I use test accuracy on test data for evaluation, but I find many fluctuations as shown in the figure below, So please how can I avoid this fluctuation ?
seni
  • 659
  • 1
  • 8
  • 20
3
votes
1 answer

how "data" and "target" are choosen in a federated learning? (PySyft)

i can't understand how in function train() below, the variable (data, target) are choosen. def train(args, model, device, federated_train_loader, optimizer, epoch): model.train() for batch_idx, (data, target) in…
AleSsAnDrOll3991
  • 31
  • 1
  • 2
3
votes
0 answers

Federated learning using custom model in Pytorch/Pysyft

I am trying to build a federated learning model. In my scenario, I have 3 workers and an orchestrator. The workers start the training and at the end of each training round, the models are being sent to the orchestrator, the orchestrator calculates…
Niki Papagora
  • 31
  • 4
2
votes
0 answers

In FedAvg what is the client optimizer?

In federated averaging, does the client optimizer have to be 'SGD' only? In this paper ADAPTIVE FEDERATED OPTIMIZATION it states "One such method is FEDAVG (McMahan et al., 2017), in which clients perform multiple epochs of SGD on their local…
Dushi Fdz
  • 161
  • 3
  • 22
2
votes
1 answer

Unbalanced client size in federated learning

I am applying federated learning on multiple files using Tensoflow Federated. The problem is, that the size of data (number of records) in each file is different. Is it a problem in federated learning training to have different sizes for each…
Alwani
  • 125
  • 8
2
votes
1 answer

Get ValueError when apply transfer learning in federated learning (TFF)

I want to use pre_trained model in federated learning as following code: first I build my model and set the weights on model and then I freeze convolutional layers and remove 4 last layer. def create_keras_model(): model = Sequential() …
Hamid Ebrahimi
  • 41
  • 4
2
votes
1 answer

Cant to install tensorflow_federated

I try to install tensorflow federated. pip install --quiet --upgrade tensorflow_federated_nightly but when I want to import tensorflow federated, I get this warning and after that google colab notebook is restarted. WARNING:tensorflow:Please fix…
Hamid Ebrahimi
  • 41
  • 4
2
votes
1 answer

AttributeError: 'MapDataset' object has no attribute 'client_ids' in tensorflow_federated TFF

I'm trying to test a compression technique in federated learning with non-IID using this API tff.simulation.datasets.build_single_label_dataset(), following these posts: TensorFlow Federated: How to tune non-IIDness in federated…
user18969005
  • 87
  • 6
2
votes
1 answer

Using create_tf_dataset_for_client() to define the training examples in the dataset

I am preparing a dataset for federation settings, in the code below, I have multiple CSV files and used each is considered a single client. dataset_paths = { 'client_0': '/content/drive/ds1.csv', 'client_1': '/content/drive/ds2.csv', …
Eden
  • 325
  • 3
  • 13
1
2 3
…
11 12