Name: Hongyan Chang
Type: User
Company: National University of Singapore
Bio: Ph.D. student at the National University of Singapore. Research interests: Algorithmic Fairness, Privacy, Federated Learning.
Twitter: Hongyan_Chang
Location: Singapore
Blog: https://www.comp.nus.edu.sg/~hongyan/
Hongyan Chang's Projects
Config files for my GitHub profile.
Writeups of Capture The Flag Competitions
JAX-based neural network library
FedML - The federated learning and analytics library enabling secure and collaborative machine learning on decentralized data anywhere at any scale. Supporting large-scale cross-silo federated learning, cross-device federated learning on smartphones/IoTs, and research simulation. MLOps and App Marketplace are also enabled (https://open.fedml.ai).
FFCV: Fast Forward Computer Vision (and other ML workloads!)
Datasets derived from US census data
ACM consolidated LaTeX styles
to diff latex file with preview versions
A collection of useful .gitignore templates
Communication-efficient decentralized SGD (Pytorch)
A state-of-the-art semi-supervised method for image recognition
Code for MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks
:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
CS3243 Introduction to AI Term Project: AI Poker
Select LaTeX colors with proper WCAG color contrast
Pytorch reimplementation of "One pixel attack for fooling deep neural networks"
Training PyTorch models with differential privacy
An open framework for Federated Learning.
The vulnerability of the neural network under data poisoning attacks