baobunuo

100days-ML-code

100天机器学习 （翻译+ 实操）

2019-CCF-BDCI-Car_sales

2019年CCF大数据与计算智能大赛乘用车细分市场销量预测冠军解决方案

adv-attacks-vae

Code to reproduce the experiments of the paper "Adversarial Attacks on Variational Autoencoders" - Gondim-Ribeiro et al., 2018.

AdvBox

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

adversarial-attack-on-GMM-i-vector-based-speaker-verification-systems

Implementation of Adversarial Attacks on GMM i-vector based Speaker Verification Systems (ICASSP2020) https://arxiv.org/abs/1911.03078

Adversarial-Contrastive-Learning

[NeurIPS 2020] “ Robust Pre-Training by Adversarial Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang

adversarial-recommender-systems-survey

The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.

AdversarialAttack

Creating an Adversarial Attack and Implementing Techniques to prevent them

Chinese_Rumor_Dataset

中文谣言数据

Deep-Learning-with-PyTorch-Tutorials

深度学习与PyTorch入门实战视频教程 配套源代码和PPT

baobunuo/adversarial-recommender-systems-survey

The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.

baobunuo/apachecn-dl-zh

ApacheCN 深度学习译文集

baobunuo/best-of-ml-python

🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.

baobunuo/cogdl

CogDL: An Extensive Research Toolkit for Graphs

baobunuo/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

baobunuo/GEM

baobunuo/GitHub-Chinese-Top-Charts

:cn: GitHub中文排行榜，帮助你发现高分优秀中文项目、更高效地吸收国人的优秀经验成果；榜单每周更新一次，敬请关注！

baobunuo/gold-miner

🥇掘金翻译计划，可能是世界最大最好的英译中技术社区，最懂读者和译者的翻译平台：

baobunuo/google-research

Google Research

baobunuo/graph-hashing

A toolbox of randomized hashing algorithms for fast Graph Representation and Network Embedding.

baobunuo/graphAnonymization

baobunuo/kepler.gl

Kepler.gl is a powerful open source geospatial analysis tool for large-scale data sets.

baobunuo/link_stealing_attack

baobunuo/littleballoffur

Little Ball of Fur - A graph sampling extension library for NetworKit and NetworkX (CIKM 2020)

baobunuo/nebula

A distributed, fast open-source graph database featuring horizontal scalability and high availability

baobunuo/ny-airbnb-analysis

Build an interactive web app with streamlit, plotly and folium

baobunuo/pomegranate

Fast, flexible and easy to use probabilistic modelling in Python.

baobunuo/Privacy-Limits-in-Bipartite-Networks-under-Active-Attacks

This work considers active deanonymization of bipartite networks. The scenario arises naturally in evaluating privacy in various applications such as social networks, mobility networks, and medical databases. For instance, in active deanonymization of social networks, an anonymous victim is targeted by an attacker (e.g. the victim visits the attacker's website), and the attacker queries her group memberships (e.g. by querying the browser history) to deanonymize her. In this work, the fundamental limits of privacy, in terms of the minimum number of queries necessary for deanonymization, is investigated. The bipartite network is generated based on linear and sublinear preferential attachment, and the stochastic block model. The victim's identity is chosen randomly based on a distribution modeling the users' risk of being the victim (e.g. probability of visiting the website). An attack algorithm is proposed which builds upon techniques from communication with feedback, and its performance, in terms of expected number of queries, is analyzed. Simulation results are provided to verify the theoretical derivations. In this project, we provide several simulations of synthesized and real-world attacks to verify the theoretical results presented in the paper and gain further intuition regarding the users’ privacy risks under such attack scenarios. For detailed problem formulation you can visit the following paper: https://arxiv.org/abs/2106.04766

baobunuo/pyro_Classification_graph_classification

The objective of this project is to infer to a graph’s latent space using Variational Inference in order to successfully represent an undirected graph into a latent space and predict the class of each node. Graphs represent objects and their relationships in the real world, popular examples are the social networks, biological networks, road networks and many more can be represented using graphs. The non-regularity of data structures have led to advancements in Graph Neural Networks in relation to tasks such as classification, predictions, etc. Recently, Kipf and Welling [T. N. Kipf and Welling 2017] proposed the Graph Convolutional Network (GCN), which is considered one of the basic Graph Neural Network variants. In the GCNs the model learns the features by inspecting the neighboring nodes. Inspired by the paper “Neural Relational Inference for Interacting Systems” [T. Kipf et al. 2018] we implemented a Variational Encoder-Decoder Structured Classifier which receives as input a graph, meaning its adjacency matrix and dictionary, and outputs the classification result. The relaxation of the discrete latent state will be executed by using the Concrete distribution (CONtinuous disCRETE) proposed in the paper “Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings” [Elinas, Bonilla, and Tiao 2020]. Our goal is to develop a model which will learn a good latent representation of graphs, while accurately predicting the node’s subject.

baobunuo/pyrobdean

Implementation of the robust de-anonymization method

baobunuo/Python-1

My Python Examples

baobunuo/PythonCodingTime

公众号「Python编程时光」 干货目录

baobunuo/rl-policies-attacks-defenses

Adversarial attacks on Deep Reinforcement Learning (RL)

baobunuo/Seed_Based_Graph_De-Anonymization_Project

Seed Based Graph De-Anonymization Project for CSC4223/6223 Privacy

baobunuo/SGC

official implementation for the paper "Simplifying Graph Convolutional Networks"

baobunuo/SimP-GCN

Implementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"

baobunuo/Spectral-Clustering-with-Graph-Neural-Networks-for-Graph-Pooling

Experimental results obtained with the MinCutPool layer as presented in the 2020 ICML paper "Spectral Clustering with Graph Neural Networks for Graph Pooling"

baobunuo/vaex

Out-of-Core DataFrames for Python, ML, visualize and explore big tabular data at a billion rows per second 🚀

baobunuo/vgae_pytorch

This repository implements variational graph auto encoder by Thomas Kipf.

baobunuo/WWW2020-O2MAC

WWW2020-One2Multi Graph Autoencoder for Multi-view Graph Clustering