Learning Stable Predictors from Weak Supervision under Distribution Shift

1. 1Formalize supervision drift as changes in P(y | x, c) across contexts
2. 2Study supervision drift in CRISPR-Cas13d experiments using RNA-seq responses
3. 3Develop methods to learn stable predictors from weak supervision under distribution shift
4. 4Evaluate the robustness of the learned predictors under different distribution shifts

Machine learning researchers and data scientists on a team benefit from this study as it provides insights into learning from weak supervision and handling distribution shifts, which is crucial for developing robust models

💡 Supervision drift can significantly impact the robustness of predictors learned from weak supervision, and formalizing it is crucial for developing stable models

🚀 Learning stable predictors from weak supervision under distribution shift 🚀