发表机构
Cornell University; Cornell Tech; Weill Cornell Medicine（康奈尔大学; 康奈尔科技学院; 威尔康乃尔医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多模态医学模型在输入缺失或模态主导时性能不佳的问题，提出ShapKO动态训练策略，基于验证效用学习特定模态剔除概率，通过评估性能、估计重要性和更新概率促进互补表示，在多数据集上提升了模型性能。
AI 中文摘要
多模态医学模型在输入缺失时往往性能下降，这在实际临床工作流程中很常见。此外，即使所有模态都存在，训练时也会出现模态主导现象，导致部分可用时鲁棒性差。虽然训练时模态剔除可提高缺失模态鲁棒性，但现有方法使用的静态掩码率无法适应训练中不断变化的模态效用。我们引入ShapKO，一种基于验证效用学习特定模态剔除概率的动态训练策略。ShapKO定期评估跨模态子集的性能，通过Shapley值估计模态重要性，并更新掩码概率以更频繁地抑制主导模态。这种自适应过程促进了互补表示，且无需架构修改。我们在三个数据集上评估了ShapKO，它在模态缺失时持续提高性能，并产生可解释的学习掩码行为轨迹。
英文摘要
Multimodal medical models often degrade when inputs are missing, a common scenario in real-world clinical workflows. Separately, even when all modalities are present, modality dominance is observed during training, where optimization over-relies on a highly predictive modality and undertrains complementary sources, resulting in poor robustness under partial availability. While training-time modality knockout improves missing-modality robustness, existing approaches use static masking rates that cannot adapt to evolving modality utility during training. We introduce ShapKO (Shapley-Adaptive Modality Knockout), a dynamic training strategy that learns modality-specific knockout probabilities based on validation utility. ShapKO periodically evaluates performance across modality subsets, estimates modality importance via Shapley values, and updates masking probabilities to suppress dominant modalities more frequently. This adaptive process promotes complementary representations, while requiring no architectural modifications. We evaluate ShapKO on three datasets covering multitask clinical classification, survival prediction, and cancer detection. ShapKO consistently improves performance under modality absence and yields interpretable trajectories of learned masking behavior. Code is available at: https://github.com/sumona00/ShapKO
