Xueying Ding
PhD Student In Public Policy And Machine Learning at Machine Learning Department at CMU
Pittsburgh, Pennsylvania, United States
Summary
🤩
Rockstar🎓
Top SchoolXueying Ding is a PhD student at Carnegie Mellon University combining public policy and machine learning with nine years of research and engineering experience. She develops and unifies diffusion models for discrete and categorical data, applying stochastic differential equations and transformer architectures to improve generation across images, music, and text. Her applied work spans physics-informed time-series models and Bayesian root-cause detection for industrial systems, as well as anomaly detection tools—she implemented the dual-autoencoder AnomalyDAE in the popular pygod graph outlier detection library. Comfortable moving between theory and production, she has delivered competitive results on IS/FID, BLEU, and domain-specific benchmarks while building human-in-the-loop visualization prototypes. Based in Pittsburgh, she blends rigorous ML foundations with policy-minded evaluation and a knack for translating complex models into usable systems.
9 years of coding experience
3 years of employment as a software developer
Bachelor’s Degree, Computer Science, 3.91, Bachelor’s Degree, Computer Science, 3.91 at Vanderbilt UniversityMaster's degree, Machine Learning, Master's degree, Machine Learning at Carnegie Mellon University
Github Skills (8)
pytorch10
deep-learning10
pytorch-geometric10
graph-neural-network10
anomaly-detection10
python10
outlier-detection10
machine-learning9
Programming languages (1)
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:18 commits, 4 pushes in 2 months
Contributions summary:Xueying implemented the AnomalyDAE model, a dual autoencoder for anomaly detection on attributed networks, within the pygod library. Their contributions involved defining the model architecture, including StructureAE and AttributeAE components, and integrating it with the BaseDetector class. They also added the loss function and the training/evaluation loop, demonstrating expertise in PyTorch and its related libraries for graph neural networks and anomaly detection.
graph-anomaly-detectionpytorchanomalypythonsecurity-tools
xyvivian/survey-physics-based-NN
Feb 2021 - Feb 2021
Contributions:12 commits, 11 pushes, 1 branch in 1 day
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.