amitport / eden-distributed-mean-estimation

This repository is the official implementation of 'EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning' (ICML 2022).

EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning

This repository is the official implementation of 'EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning' presented at ICML 2022.

Context

EDEN is a lossy unbiased compression technique for distributed mean estimation that handles heterogeneous communication budgets and packet losses naturally and simply.

Folder structure

The torch and tf folders contain EDEN's implementation in PyTorch and TensorFlow, respectively.

Citation

If you find this useful, please cite us:

@InProceedings{pmlr-v162-vargaftik22a,
  title = 	 {{EDEN}: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning},
  author =       {Vargaftik, Shay and Basat, Ran Ben and Portnoy, Amit and Mendelson, Gal and Itzhak, Yaniv Ben and Mitzenmacher, Michael},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {21984--22014},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/vargaftik22a/vargaftik22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/vargaftik22a.html},
  abstract = 	 {Distributed Mean Estimation (DME) is a central building block in federated learning, where clients send local gradients to a parameter server for averaging and updating the model. Due to communication constraints, clients often use lossy compression techniques to compress the gradients, resulting in estimation inaccuracies. DME is more challenging when clients have diverse network conditions, such as constrained communication budgets and packet losses. In such settings, DME techniques often incur a significant increase in the estimation error leading to degraded learning performance. In this work, we propose a robust DME technique named EDEN that naturally handles heterogeneous communication budgets and packet losses. We derive appealing theoretical guarantees for EDEN and evaluate it empirically. Our results demonstrate that EDEN consistently improves over state-of-the-art DME techniques.}
}

eden-distributed-mean-estimation's Issues

AttributeError: module 'tensorflow_federated.python.learning' has no attribute 'Model'. Did you mean: 'models'?

I am trying to reproduce the experiment at my end.
I am using the TensorFlow implementation.
On running the trainer.py file I am getting the error as mentioned in the title of the issue.
Please see below

2023-08-24 23:00:46.600033: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2023-08-24 23:00:46.623500: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-08-24 23:00:46.974261: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Traceback (most recent call last):
File "/home/sourish-wicon-lab/fedlen/EDEN-Distributed-Mean-Estimation/tf/trainer.py", line 7, in
import fed_avg_schedule
File "/home/sourish-wicon-lab/fedlen/EDEN-Distributed-Mean-Estimation/tf/fed_avg_schedule.py", line 37, in
ModelBuilder = Callable[[], tff.learning.Model]
AttributeError: module 'tensorflow_federated.python.learning' has no attribute 'Model'. Did you mean: 'models'?

I have checked the documentation of tensorflow_federated and found that tensorflow_federated.python.learning has module named models instead of Model
Please help me clarify what I am doing wrong?