Research map / Federated learning and privacy / Personalized and heterogeneous FL
Privacy-Protected Causal Survival Analysis Under Distribution Shift
Yi Liu, Alexander W. Levis, Ke Zhu, Shu Yang, Peter B. Gilbert, Larry Han
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| borrow source sites with adaptive weights (FED) instead of using the target site only (TGT) | federated survival estimator · simulation, 5 shift scenarios, day 30 | RMSE: up to 59% reductions in RMSE | Improved |
| use FED instead of META-IVW under outcome shift | federated survival estimator · simulation, Outcome Shift and All Shifts | bias | Improved |
| use FED instead of POOL or IVW under covariate, outcome or all shifts | federated survival estimator · simulation, shifted scenarios | coverage probability | Improved |
| limit target-site propensity overlap | FED · simulation, limited overlap | efficiency gain | Improved |
| evaluate at earlier time points rather than later | FED · simulation, all scenarios | efficiency gain | Improved |
| use FED instead of TGT when events are rare early on | federated survival estimator · AMP trials, SA target | confidence interval availability | Improved |
| use l1 penalty on discrepancy-weighted site weights | FED · simulation | site weight | Improved |
Closest papers by meaning
- Fair Federated Survival Analysis (AAAI 2025 · similarity 0.87)
- Federated Causal Discovery from Heterogeneous Data (ICLR 2024 · similarity 0.86)
- Collaborative Heterogeneous Causal Inference Beyond Meta-analysis (ICML 2024 · similarity 0.86)
- Differentially private learners for heterogeneous treatment effects (ICLR 2025 · similarity 0.84)
- Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments (ICML 2025 · similarity 0.84)
- Multi-Source Conformal Inference Under Distribution Shift (ICML 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
