动态调整模态剔除策略，提升多模态医疗模型在数据缺失时的鲁棒性。
ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning
- 基于Shapley值动态评估模态重要性，自适应调整剔除概率
- 在三种临床数据集上均显著提升模态缺失下的性能
- 无需修改模型结构，结果可解释性强，适合医疗场景
多模态医疗模型在输入缺失时性能常下降，这在真实临床工作中很常见。即使所有模态都存在，训练中也常出现模态主导现象：优化过度依赖高预测性模态，忽略互补信息，导致部分模态缺失时鲁棒性差。现有训练时模态剔除方法采用固定剔除率，无法随训练过程中的模态效用变化调整。本文提出ShapKO（Shapley-Adaptive Modality Knockout），一种动态训练策略，通过验证集表现定期评估模态子集性能，利用Shapley值估计各模态重要性，并动态更新剔除概率，更频繁剔除主导模态。该策略促进互补表征学习，且无需架构改动。在覆盖多任务临床分类、生存预测和癌症检测的三个数据集上，ShapKO consistently 提升了模态缺失情况下的表现，并生成可解释的剔除行为轨迹。代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。