An Experience Report on Machine Learning Reproducibility: Guidance for Practitioners and TensorFlow Model Garden Contributors
Paper
•
2107.00821
•
Published
Wenxin Jiang
jiang784
·
AI & ML interests
My research interest is focused on SE4AI, and Responsible AI. I currently work on advancing AI safety/security and utility, more specifically on improving reusability, trustworthiness, and security of pre-trained deep learning models (PTMs) from model registries/hubs.
Organizations
authored
5
papers
about 2 years ago
Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Vision
Paper
•
2303.07476
•
Published
An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry
Paper
•
2303.02552
•
Published
Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem
Paper
•
2303.17708
•
Published
PTMTorrent: A Dataset for Mining Open-source Pre-trained Model Packages
Paper
•
2303.08934
•
Published