发表机构
University of Lausanne; HEC Lausanne; BegooAI（洛桑大学; 洛桑高等商学院; 贝古人工智能公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多模态回归中模态缺失或分歧导致预测区间难校准的问题，提出感知模态的共形校准层，在多组实验中提升了区间性能，尤其在模态缺失时恢复了覆盖率。
AI 中文摘要
当多模态回归的输入源（表格变量、文本、图像或其他来源）存在分歧或某一输入缺失时，其预测区间难以校准。单一全局分位数会将这些情况平均处理，而非针对测试时观察到的模态模式进行校准。我们通过一个感知模态的共形校准层解决该问题：该层针对每种模态训练或复用一个预测器，从其预测结果计算分歧分数，并在严格拆分协议下将该分数用于拆分共形校准。我们以两种互补方式使用该分数：其一，连续分歧缩放方法在保留常规边际拆分共形保证的同时，跨样本重新分配区间宽度；其二，Mondrian（分层）方法在校准前由分歧或模态可用性定义的组内进行校准，在校准与测试样本联合可交换性下提供组级保证。在四个多模态数据集上，分歧缩放层在60次配对运行中，区间连续排名概率得分（CRPS）与边际共形基线持平或更优的情况有59次；在区间宽度上持平或更优的情况有52次，同时保持经验覆盖率接近95%的目标。在模态缺失的压力测试中，掩码匹配的重新校准在最难的固定掩码 regime中恢复了多达19.5个百分点的覆盖率。最终得到一个简单、与模型无关的多模态回归系统的可靠性层，项目页面可访问this https URL。
英文摘要
Prediction intervals for multi-modal regression with tabular variables, text, images, or other input sources are difficult to calibrate when those sources disagree or one is missing. A single global quantile averages these regimes together instead of calibrating to the modality pattern observed at test time. We address this through a modality-aware conformal calibration layer. The layer trains or reuses one predictor per modality, computes a disagreement score from their predictions, and uses that score in split conformal calibration under a strict split protocol. We use the score in two complementary ways. First, a continuous disagreement-scaled method reallocates interval width across examples while preserving the usual marginal split-conformal guarantee. Second, a Mondrian (stratified) method calibrates within groups defined by disagreement or modality availability fixed before calibration, giving group guarantees under joint exchangeability of the calibration and test examples. Across four multi-modal datasets, the disagreement-scaled layer matches or improves the marginal conformal baseline in 59 of 60 paired runs for interval continuous ranked probability score (CRPS) and in 52 of 60 for interval width, while keeping empirical coverage near the 95% target. In stress tests with missing modalities, mask-matched recalibration recovers up to 19.5 percentage points of coverage in the hardest fixed-mask regime. The result is a simple, model-agnostic reliability layer for multi-modal regression systems. A project page is available at https://unco3892.github.io/modality-aware-conformal.
CommentsPublished at the Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2026)
