Research map / Label-efficient and robust learning / Semi-supervised learning
Differentiable sorting for censored time-to-event data.
Andre Vauvelle, Benjamin Wild, Roland Eils, Spiros Denaxas
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 |
|---|---|---|---|
| Replace Cox partial likelihood with Diffsurv at risk set size 4 | survSVHN CNN · survSVHN n=4 | C-index: .925 -> .934 | Improved |
| Replace Cox partial likelihood with Diffsurv at risk set size 8 | survSVHN CNN · survSVHN n=8 | C-index: .931 -> .940 | Improved |
| Replace Cox partial likelihood with Diffsurv at risk set size 16 | survSVHN CNN · survSVHN n=16 | C-index: .933 -> .943 | Improved |
| Replace Cox partial likelihood with Diffsurv at risk set size 32 | survSVHN CNN · survSVHN n=32 | C-index: .930 -> .941 | Improved |
| Risk set size 2 where both methods reduce to the ranking loss | Diffsurv vs Cox · survSVHN n=2 | C-index: .913 -> .918 | No clear effect |
| Increase risk set size from 2 to 16 for Diffsurv | Diffsurv · survSVHN | C-index: .918 -> .943 | Improved |
| Increase risk set size from 16 to 32 for Diffsurv | Diffsurv · survSVHN | C-index: .943 -> .941 | No clear effect |
| Replace Cox partial likelihood with Diffsurv | MLP · SUPPORT | C-index: .584 -> .599 | Improved |
| Replace Cox partial likelihood with Diffsurv | MLP · FLCHAIN | C-index: .787 -> .787 | No clear effect |
| Replace Cox partial likelihood with Diffsurv | MLP · NWTCO | C-index: .690 -> .691 | No clear effect |
| Replace Cox partial likelihood with Diffsurv | MLP · METABRIC | C-index: .615 -> .623 | No clear effect |
| Optimize Diffsurv for top-10% risk prediction instead of Cox | MLP · SUPPORT | top 10% proportion correct: .478 -> .571 | Improved |
Closest papers by meaning
- Boosting Methods for Interval-censored Data with Regression and Classification (ICLR 2025 · similarity 0.85)
- Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data (NeurIPS 2025 · similarity 0.82)
- Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring (NeurIPS 2026 · similarity 0.82)
- Deep Copula-Based Survival Analysis for Dependent Censoring with Identifiability Guarantees (AAAI 2024 · similarity 0.82)
- DiffPO: A causal diffusion model for learning distributions of potential outcomes (NeurIPS 2024 · similarity 0.82)
- FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models (NeurIPS 2024 · similarity 0.82)
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.
