FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation

Last update: Jun 29, 2022

Related tags

Overview

This repository contains the code accompanying the paper " FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation" Paper link:

Requirements to run the code:

Python 3.7
Tensorflow 1.14.0
numpy 1.20.3
tqdm

Download dataset:

Download mnistm data:

curl -L -O http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/BSR/BSR_bsds500.tgz

Preprocess mnistm dataset

python create_mnistm.py

Experiments on Federated Domain Adaptation:

Usage for the Proposed FedMM on DANN loss:

python train.py -max_iter=15000 -lambda1_decay=1.05 -adv_loss='DANN'

Usage for the Proposed FedMM on MDD loss:

python train.py -max_iter=50000 -lambda1_decay=1.01 -adv_loss='MDD'

Usage for the Proposed FedMM on CDAN loss

python train.py -max_iter=30000 -lambda1_decay=1.02 -adv_loss='CDAN'

Reference

@misc{2110.08477,
Author = {Yan Shen and Jian Du and Hao Zhang and Benyu Zhang and Zhanghexuan Ji and Mingchen Gao},
Title = {FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation},
Year = {2021},
Eprint = {arXiv:2110.08477},
}

FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation

Related tags

Overview

Requirements to run the code:

Download dataset:

Experiments on Federated Domain Adaptation:

Reference

Owner

This repository is the offical Pytorch implementation of ContextPose: Context Modeling in 3D Human Pose Estimation: A Unified Perspective (CVPR 2021).

More than a hundred strange attractors

A PyTorch implementation of "Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning", IJCAI-21

Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN

This is the repository for the AAAI 21 paper [Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning].

Towards Implicit Text-Guided 3D Shape Generation (CVPR2022)

Multi Camera Calibration

TorchGeo is a PyTorch domain library, similar to torchvision, that provides datasets, transforms, samplers, and pre-trained models specific to geospatial data.

A mini lib that implements several useful functions binding to PyTorch in C++.

Official code for the CVPR 2021 paper "How Well Do Self-Supervised Models Transfer?"

Auxiliary Raw Net (ARawNet) is a ASVSpoof detection model taking both raw waveform and handcrafted features as inputs, to balance the trade-off between performance and model complexity.

Fast convergence of detr with spatially modulated co-attention

Face Synthetics dataset is a collection of diverse synthetic face images with ground truth labels.

This is the official code of L2G, Unrolling and Recurrent Unrolling in Learning to Learn Graph Topologies.

Meta-learning for NLP

Deep Compression for Dense Point Cloud Maps.

DyNet: The Dynamic Neural Network Toolkit

Tracing Versus Freehand for Evaluating Computer-Generated Drawings (SIGGRAPH 2021)

Malware Bypass Research using Reinforcement Learning

PyTorch Implement for Path Attention Graph Network