peixj Goto Github PK
Type: User
Type: User
Differential privacy theory and code, differential private machine learning
机器学习和差分隐私的论文笔记和代码仓
Source code for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)
Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.
YC Hackathon 2018 Winner Project. BEN: A decentralized chatbot that uses federated learning.
The data scientists at BigMart have collected 2013 sales data for 1559 products across 10 stores in different cities. The aim is to build a predictive model and find out the sales of each product at a particular store.Using this predictive model the data scientists at BigMart can understand the properties of products and stores which play a key role in increasing sales. The tasks done for this project are : *Data Exploration *Data QAQC *Outlier detection and missing data replacement strategy *Data ETL *Understanding about sales domain *Feature Engineering *Advanced Data Analysis *Regression modeling Techniques *Hybrid modeling Techniques *Specific measure to Evaluate Model The datasets were acquired from : https://s3.amazonaws.com/hackerday.datascience/49/Test_u94Q5KV.csv https://s3.amazonaws.com/hackerday.datascience/49/Train_UWu5bXk.csv https://s3.amazonaws.com/hackerday.datascience/49/SampleSubmission_TmnO39y.csv Software Requirements : Continuum Analytics, Inc software Python 2.7 version with seaborn package was used.
Some notes on things I find interesting and important.
基于pymetis的Cluster-GCN,参考自https://github.com/benedekrozemberczki/ClusterGCN,略作修改
This repo contains implementation of different architectures for emotion recognition in conversations.
Code for Data Poisoning Attacks Against Federated Learning Systems
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19
特征提取/数据降维:PCA、LDA、MDS、LLE、TSNE等降维算法的python实现
This project's goal is to evaluate the privacy leakage of differentially private machine learning models.
A Keras implementation of FederatedAvergaing [McMahan, Brendan, et al. 2017] and Lazily Aggregated Stochastic Gradients [Chen, Tianyi, Yuejiao Sun, and Wotao Yin. 2020]
联邦学习
Implementation of Communication-Efficient Learning of Deep Networks from Decentralized Data
Implementation of the paper "Adversarial Attacks on Graph Neural Networks via Meta Learning".
A list of recent papers about Graph Neural Network methods applied in NLP areas.
Source code and dataset of the NeurIPS 2020 paper "Graph Random Neural Network for Semi-Supervised Learning on Graphs"
Autoencoders for Link Prediction and Semi-Supervised Node Classification (DSAA 2018)
Implementation and experiments of graph embedding algorithms.deep walk,LINE(Large-scale Information Network Embedding),node2vec,SDNE(Structural Deep Network Embedding),struc2vec
Graph Cross Network
Implementation of the paper "NetGAN: Generating Graphs via Random Walks".
Implementation of the paper "Adversarial Attacks on Neural Networks for Graph Data".
研读顶会论文,复现论文相关代码
Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle
Semi-supervised learning with graph embeddings
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.