Research map / Continual learning / Online and replay-based
ConSurv: Multimodal Continual Learning for Survival Analysis
Dianzhi Yu, Conghao Xiong, Yankai Chen, Wenqian Cui, Xinni Zhang, Yifei Zhang, Hao Chen, Joseph J. Y. Sung, Irwin King
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 |
|---|---|---|---|
| add MS-MoE to finetuning (ablation) | Finetune · MSAIL (Order-I) | average C-index: 0.572 -> 0.585 | Improved |
| add MS-MoE to finetuning (ablation) | Finetune · MSAIL (Order-I) | average C-index IPCW: 0.528 -> 0.575 | Improved |
| add FCR to finetuning (ablation) | Finetune · MSAIL (Order-I) | average C-index: 0.572 -> 0.581 | Improved |
| add FCR to finetuning (ablation) | Finetune · MSAIL (Order-I) | average C-index IPCW: 0.528 -> 0.545 | Improved |
| add FCR to finetuning (ablation) | Finetune · MSAIL (Order-I) | forgetting C-index: 0.094 -> 0.121 | Hurt |
| add feature constraints at patch, genomics and fusion levels instead of fusion only (ablation) | MS-MoE + FCR (f) · MSAIL (Order-I) | average C-index: 0.599 -> 0.601 | Improved |
| add feature constraints at all three levels instead of fusion only (ablation) | MS-MoE + FCR (f) · MSAIL (Order-I) | average C-index IPCW: 0.554 -> 0.597 | Improved |
| add MS-MoE to FCR (ablation) | FCR only · MSAIL (Order-I) | average C-index IPCW: 0.545 -> 0.597 | Improved |
| use ConSurv instead of DER++ | DER++ · MSAIL (Order-I) | average C-index: 0.590 -> 0.601 | Improved |
| use ConSurv instead of IMEX-Reg | IMEX-Reg · MSAIL (Order-I) | average C-index IPCW: 0.589 -> 0.597 | Improved |
| use ConSurv instead of Finetune | Finetune · MSAIL (Order-I) | average C-index: 0.572 -> 0.601 | Improved |
| use ER replay instead of plain finetuning | Finetune · MSAIL (Order-I) | average C-index: 0.572 -> 0.561 | Hurt |
Closest papers by meaning
- Distilled Prompt Learning for Incomplete Multimodal Survival Prediction (CVPR 2025 · similarity 0.88)
- Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction (ICLR 2024 · similarity 0.88)
- A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature (NeurIPS 2026 · similarity 0.88)
- CA-MLIF: Cross-Attention and Multimodal Low-Rank Interaction Fusion Framework for Tumor Prognostic Prediction (AAAI 2025 · similarity 0.86)
- Multimodal Prototyping for cancer survival prediction (ICML 2024 · similarity 0.86)
- Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning (CVPR 2024 · similarity 0.86)
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.
