Code for Subgraph Federated Learning with Missing Neighbor Generation (NeurIPS 2021)

Related tags

Deep Learning fedsage
Overview

To run the code

  1. Unzip the package to your local directory;
  2. Run 'pip install -r requirements.txt' to download required packages;
  3. Open file ~/nips_code/src/utils/config.py;
  4. Replace the "change_to_your_current_path" in line 2 of config.py (root_path= "change_to_your_current_path") to your current path;
    • You can change hyper-parameters in config.py according to different testing scenarios;
  5. Run the whole pipline with 'python ~/nips_code/src/system_test.py'.

If you find this work useful for your research, please cite

@inproceedings{zhang2021subgraph,
  title={Subgraph federated learning with missing neighbor generation},
  author={Zhang, Ke and Yang, Carl and Li, Xiaoxiao and Sun, Lichao and Yiu, Siu Ming},
  booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
  year={2021}
}
You might also like...
noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.

ProSelfLC: CVPR 2021 ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks For any specific discussion or potential fu

amos_xwang 57 Dec 4, 2022
Python package for missing-data imputation with deep learning
Python package for missing-data imputation with deep learning

MIDASpy Overview MIDASpy is a Python package for multiply imputing missing data using deep learning methods. The MIDASpy algorithm offers significant

MIDASverse 77 Dec 3, 2022
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

Simple and Robust Loss Design for Multi-Label Learning with Missing Labels Official PyTorch Implementation of the paper Simple and Robust Loss Design

Xinyu Huang 28 Oct 27, 2022
A Research-oriented Federated Learning Library and Benchmark Platform for Graph Neural Networks. Accepted to ICLR'2021 - DPML and MLSys'21 - GNNSys workshops.

FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks A Research-oriented Federated Learning Library and Benchmark Platform

FedML-AI 175 Dec 1, 2022
Official code implementation for
Official code implementation for "Personalized Federated Learning using Hypernetworks"

Personalized Federated Learning using Hypernetworks This is an official implementation of Personalized Federated Learning using Hypernetworks paper. [

Aviv Shamsian 121 Dec 25, 2022
This is the formal code implementation of the CVPR 2022 paper 'Federated Class Incremental Learning'.
This is the formal code implementation of the CVPR 2022 paper 'Federated Class Incremental Learning'.

Official Pytorch Implementation for GLFC [CVPR-2022] Federated Class-Incremental Learning This is the official implementation code of our paper "Feder

Race Wang 57 Dec 27, 2022
Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )

Differential Privacy (DP) Based Federated Learning (FL) Everything about DP-based FL you need is here. （所有你需要的DP-based FL的信息都在这里） Code Tip: the code o

wenzhu 83 Dec 24, 2022
The missing CMake project initializer

cmake-init - The missing CMake project initializer Opinionated CMake project initializer to generate CMake projects that are FetchContent ready, separ

null 1k Jan 1, 2023
(SIGIR2020) “Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback’’

Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback About This repository accompanies the real-world experiments conducted i

yuta-saito 19 Dec 1, 2022
Comments
  • Could you share a more detailed hyperparameter setting?

    Could you share a more detailed hyperparameter setting?

    Thanks for your great work! When I run the code with the hyperparameters you provided in your paper, eg.:

    # config.py

dataset = "cora"
num_owners = 3
delta=20

num_samples = [5,5]
batch_size = 64
latent_dim=128
steps=10
epochs_local=1
lr=0.001
weight_decay=1e-4
hidden=32
dropout=0.5

gen_epochs=20
num_pred=5
hidden_portion=0.278

epoch_classifier=50
classifier_layer_sizes=[64,32]

    I get the results:

    FedSage+ end!

1/9 [==>...........................] - ETA: 3s - loss: 0.7960 - acc: 0.8281
3/9 [=========>....................] - ETA: 0s - loss: 0.7997 - acc: 0.8316
7/9 [======================>.......] - ETA: 0s - loss: 0.8128 - acc: 0.8331
9/9 [==============================] - 1s 18ms/step - loss: 0.8080 - acc: 0.8358

1/9 [==>...........................] - ETA: 3s - loss: 0.1631 - acc: 0.9688
4/9 [============>.................] - ETA: 0s - loss: 0.2067 - acc: 0.9469
7/9 [======================>.......] - ETA: 0s - loss: 0.2316 - acc: 0.9389
9/9 [==============================] - 1s 18ms/step - loss: 0.2372 - acc: 0.9366

Global model

Global Test Set Metrics:
	loss: 0.2478
	acc: 0.9317

    I think the test acc for FedSage+ is 0.8358, and the test acc for GlobSage is 93.17 (Correct me if I misunderstand), which has a gap to the reported results in your paper. Therefore, could you share a more detailed hyperparameter setting to reproduce the reported results? (eg., epochs_local, classifier_layer_sizes, gen_epochs, etc.)

    opened by rayrayraykk 3
  • Question about the classifiers

    Question about the classifiers

    I have some questions about the use of classifiers:

    The classifiers you used to train the neighbor generator in models.py is: self.classifier=GNN(nfeat=feat_shape, nhid=config.hidden, nclass=n_classes, dropout=config.dropout) But the classifier you used in classifiers.py for the task is: graphsage_model=GraphSAGE(layer_sizes=config.classifier_layer_sizes, generator=fillG_node_gen, n_samples=config.num_samples)

    I would like to know why not use the same classifier (eg. GraphSAGE) instead of using the expanded graph to train a new classifier?

    opened by AnonymousGeeek 0
  • Packages for CUDA 10.1 environment

    Packages for CUDA 10.1 environment

    Since that requirements need CUDA >=11.0, I have tried code on CUDA 10.1 like below:

    pip install torch==1.7.1
pip install tensorflow==2.3.2
pip install dill==0.3.3
pip install louvain==0.7.0
pip install pandas==1.2.1
pip install scikit_learn==1.0
pip install stellargraph==1.2.1
pip install python-louvain
pip install chardet
pip install Keras==2.4.3

    Hope it could help you.

    opened by youngfish42 1
Owner
null
GitHub
Federated Learning - Including common test models for federated learning, like CNN, Resnet18 and lstm, controlled by different parser

Federated_Learning ?? This projest include common test models for federated lear

TianyuQi 10 Dec 11, 2022
We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

Deep GNN, Shallow Sampling Hanqing Zeng, Muhan Zhang, Yinglong Xia, Ajitesh Srivastava, Andrey Malevich, Rajgopal Kannan, Viktor Prasanna, Long Jin, R

Facebook Research 117 Dec 20, 2022
Official PyTorch implementation of the paper: Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting.

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting Official PyTorch implementation of the paper: Improving Graph Neural Net

Giorgos Bouritsas 58 Dec 31, 2022
Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)

Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)

Junxian He 57 Jan 1, 2023
Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

structshot Code and data for paper "Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning", Yi Yang and Arz

ASAPP Research 47 Dec 27, 2022
Personal implementation of paper "Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval"

Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval This repo provides personal implementation of paper Approximate Ne

John 8 Oct 7, 2022
TorchPQ is a python library for Approximate Nearest Neighbor Search (ANNS) and Maximum Inner Product Search (MIPS) on GPU using Product Quantization (PQ) algorithm.

Efficient implementations of Product Quantization and its variants using Pytorch and CUDA

null 146 Dec 28, 2022
Optimal space decomposition based-product quantization for approximate nearest neighbor search

Optimal space decomposition based-product quantization for approximate nearest neighbor search Abstract Product quantization(PQ) is an effective neare

Mylove 1 Nov 19, 2021
K-Nearest Neighbor in Pytorch

Pytorch KNN CUDA 2019/11/02 This repository will no longer be maintained as pytorch supports sort() and kthvalue on tensors. git clone https://github.

Chris Choy 65 Dec 1, 2022
Code for "Adversarial Attack Generation Empowered by Min-Max Optimization", NeurIPS 2021

Min-Max Adversarial Attacks [Paper] [arXiv] [Video] [Slide] Adversarial Attack Generation Empowered by Min-Max Optimization Jingkang Wang, Tianyun Zha

Jingkang Wang 12 Nov 23, 2022