Multimodal fusion is crucial in joint decision-making systems for rendering
holistic judgments. Since multimodal data changes in open environments, dynamic
fusion has emerged and achieved remarkable progress in numerous applications.
However, most existing dynamic multimodal fusion methods lack theoretical
guarantees and easily fall into suboptimal problems, yielding unreliability and
instability. To address this issue, we propose a Predictive Dynamic Fusion
(PDF) framework for multimodal learning. We proceed to reveal the multimodal
fusion from a generalization perspective and theoretically derive the
predictable Collaborative Belief (Co-Belief) with Mono- and Holo-Confidence,
which provably reduces the upper bound of generalization error. Accordingly, we
further propose a relative calibration strategy to calibrate the predicted
Co-Belief for potential uncertainty. Extensive experiments on multiple
benchmarks confirm our superiority. Our code is available at
this https URL

提出了一种用于多模态学习的预测动态融合（PDF）框架，通过从泛化角度揭示多模态融合，理论上推导出可预测的合作信念（Co-Belief）与单一和整体置信的关系，并进一步提出相对校准策略以校准潜在的不确定性，通过在多个基准测试上的大量实验证实了其优越性。