DP-CL(Continual Learning with Differential Privacy)

This is the official implementation of the Continual Learning with Differential Privacy.

If you use this code or our results in your research, please cite as appropriate:

@article{desai2021continual,
  title={Continual Learning with Differential Privacy},
  author={Pradnya, Desai and Lai, Phung and Phan, NhatHai and Thai, My},
  journal={International Conference on Neural Information Processing},
  year={2021}
}

Software Requirements

Python 3.7 is used for the current codebase.

Tensorflow 2.5

Experiments

The repository comes with instructions to reproduce the results in the paper or to train the model from scratch:

To reproduce the results:

Clone or download the folder from this repository.
Please find dataset on Google Drive folder.
Go to folder DP-CL/ and Run ./replicate_results_xx.sh xx 3 where xx is the name of dataset and task that you'd like to run. For example: ./replicate_results_mnist.sh MNIST 3 for MNIST, ./replicate_results_cifar100.sh CIFAR 3 for CIFAR-100, ./replicate_results_cifar10.sh CIFAR 3 for CIFAR-10.

Potential issues

If you have any issues while running the code or further information, please send email directly to the first authors of this paper ([email protected] or [email protected]).

DP-CL(Continual Learning with Differential Privacy)

Related tags

Overview

DP-CL(Continual Learning with Differential Privacy)

Software Requirements

Experiments

Potential issues

Owner

Phung Lai

A framework to train language models to learn invariant representations.

Official implementation of deep Gaussian process (DGP)-based multi-speaker speech synthesis with PyTorch.

Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch

This code is for eCaReNet: explainable Cancer Relapse Prediction Network.

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

PyTorch implementation of SCAFFOLD (Stochastic Controlled Averaging for Federated Learning, ICML 2020).

DGN pymarl - Implementation of DGN on Pymarl, which could be trained by VDN or QMIX

This is a Keras-based Python implementation of DeepMask- a complex deep neural network for learning object segmentation masks

Official code repository for the publication "Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons"

Official PyTorch implementation and pretrained models of the paper Self-Supervised Classification Network

C3DPO - Canonical 3D Pose Networks for Non-rigid Structure From Motion.

Image-to-Image Translation in PyTorch

Official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021.

Unofficial PyTorch implementation of Guided Dropout

G-NIA model from "Single Node Injection Attack against Graph Neural Networks" (CIKM 2021)

Code for the paper "Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness"

Complete the code of prefix-tuning in low data setting

Racing line optimization algorithm in python that uses Particle Swarm Optimization.

MMdet2-based reposity about lightweight detection model: Nanodet, PicoDet.