用于可信多组学多模态融合的自适应置信加权扩展
Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion
浏览论文内容
中文总结 AI 辅助
针对多模态学习模型在噪声或无信息数据流下性能不佳及缺乏数据质量评估机制的问题，提出自适应置信加权扩展（ACE）框架，通过生成互补模态和双层置信机制提升性能，在多组学数据集评估中显著优于现有算法。
中文摘要 AI 辅助
多模态学习是提高医学预后等应用预测性能的有力方法。然而，使用多模态学习的模型在噪声或无信息数据流下性能不佳，阻碍了其临床应用。当前融合方法往往缺乏对数据质量动态评估及为最终预测提供可信置信分数的稳健机制。为解决这些局限，我们引入自适应置信加权扩展（ACE）框架。ACE首先通过模态内相关性生成新的互补模态来增强多模态空间，然后采用双层置信机制，一是融合前按可靠性自适应重新加权所有模态，二是估计融合最终决策的全局信任分数。我们用四个具有挑战性的多组学数据集评估ACE，其在分类性能和置信校准方面显著优于现有算法。我们的框架提供了更稳定、稳健的数据融合方法，便于在解决高风险问题中使用多模态学习。
英文摘要
Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis. However, the clinical applicability of models that use multimodal learning is hampered by their poor performance under noisy or uninformative data streams. Present fusion approaches often lack robust mechanisms for the dynamic assessment of data quality and for the provision of a trustable confidence score on the final prediction. This dissuades their deployment in safety-critical settings. To address these limitations, we introduce Adaptive Confidence-weighted Expansion (ACE), a novel framework to enhance the trustworthiness of multimodal fusion models. ACE first enhances the multimodal space by generating new, complementary modalities from intra-modality correlations. It then employs a dual-level confidence mechanism that (1) adaptively reweighs all modalities by their reliability before fusion and (2) estimates a global trust score over the fused, final decision. To evaluate ACE, we used four challenging multi-omics datasets (BRCA, KIPAN, LGG, and ROSMAP). ACE significantly outperforms existing state-of-the-art algorithms in both classification performance and confidence calibration. Our framework provides a more stable and robust data fusion method that facilitates the use of multimodal learning in addressing high-stakes problems.
发表机构
- Faculty of Engineering, University of Ottawa（渥太华大学工程学院）
- RIV Lab, Department of Computer Engineering, Bu-Ali Sina University（布阿里·西纳大学计算机工程系RIV实验室）
- School of Computing and Communications, Lancaster University（兰卡斯特大学计算与通信学院）
机构由 AI 辅助整理，请以论文原文为准。
