Canyu Chen
Chicago, Illinois, United States
Summary
🤩
Rockstar🎓
Top SchoolCanyu Chen is a machine learning engineer and PhD candidate in computer science based in Chicago with eight years of experience building graph-based anomaly detection models and research-grade ML systems. They have contributed significant model implementations—such as COLA and ANEMONE—to the popular pygod library, demonstrating strengths in graph neural networks, contrastive learning, and production-quality integration and testing. Canyu has research experience at top institutions, including a visiting researcher stint at UC Berkeley under Prof. Dawn Song, blending academic rigor with practical open-source impact. Comfortable moving between research code and deployable libraries, they focus on interpretable, well-tested models for graph outlier detection and enjoy turning cutting-edge ideas into reusable tools.
8 years of coding experience
Doctor's Degree, Computer Science, Doctor's Degree, Computer Science at Northwestern University
Github Skills (10)
pytorch10
machine-learning10
deep-learning10
graph-neural-network10
anomaly-detection10
python10
contrastive-learning9
outlier-detection9
scikit-learn5
scikit5
Programming languages (2)
Github contributions (5)
pygod-team/pygod
Feb 2022 - Apr 2022
A Python Library for Graph Outlier Detection (Anomaly Detection)
Role in this project:
ML Engineer
ML EngineerContributions:6 commits, 4 pushes in 2 months
Contributions summary:Canyu contributed significantly to the implementation of a new graph anomaly detection model, named COLA, within the pygod library. This involved creating the model's architecture, including key components like GCN layers, discriminators, and readout functions, and integrating it with the existing codebase. Furthermore, the user developed a new model ANEMONE, showcasing expertise in contrastive learning techniques tailored for graph data. The code changes also include testing for the new models and improvements in the README.
graph-anomaly-detectionpytorchanomalypythonsecurity-tools
harvardchen/UCAS-OS
Oct 2018 - Jul 2019
Contributions:210 commits, 13 pushes, 1 branch in 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.