AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Discrete Survival Knowledge Distillation for Competing Risks Analysis

Feiyang Deng, Lingfeng Luo, Di Wang, Qinmengge Li, Lingxuan Kong, Kevin He

ICML 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives

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 changedWhereMeasuredEffect
distill a matched competing-risks teacher into the competing-risks student (DiSKD)discrete-time competing-risks student · SRTR post-COVID cohortCtd (Death): 0.5954 -> 0.6889Improved
distill an overall-event teacher into the competing-risks studentdiscrete-time competing-risks student · SRTR post-COVID cohortCtd (Graft): 0.5667 -> 0.6533Improved
use a fixed-horizon binary teacher instead of a matched competing-risks teacher (ablation)DiSKD · SRTR post-COVID cohortCtd (Death): 0.6889 -> 0.6306 (Binary-2)Hurt
use a fixed-horizon binary teacher instead of internal-only trainingcompeting-risks student · SRTR post-COVID cohortpredictive deviance: 0.4749 -> 0.4702 (Binary-1)Improved
raise distillation temperature from T=1 to T=2 (ablation)DiSKD-C with good teacher · simulation, correlated competing risksCtd and predictive devianceImproved
raise temperature further from T=3 to T=5 (ablation)DiSKD-C · simulation, correlated competing risksCtd and predictive devianceNo clear effect
use cause-specific teacher (DiSKD-C) rather than overall-event teacher (DiSKD-O) when teacher is good (ablation)DiSKD · simulation, teacher quality (a) GoodCtd and predictive devianceImproved
use cause-specific teacher rather than overall-event teacher when teacher is poor (ablation)DiSKD · simulation, teacher quality (c) PoorCtd and predictive devianceNo clear effect
distill from both teachers (multi-teacher) vs weaker teacher alone (ablation)DiSKD · simulation, two teachers with different covariatespredictive performanceImproved
add finetuning from teacher before DiSKD (Finetune+DiSKD vs DiSKD) (ablation)DiSKD · SRTR post-COVID cohortconcordance and devianceNo clear effect
use DiSKD instead of stacking (pooled training) or finetuningpost-COVID model update · SRTR post-COVID cohortconcordance-deviance trade-offImproved
distill post-COVID model into donor-only studentdonor-only student · SRTR donor-quality, post-COVID test cohortCtd death and graft failureImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy