Figure 2: Exemplar reference attribution for five representative ADNI test subjects. Each column corresponds to one query subject. The first row summarizes the ground-truth and predicted diagnosis together with selected clinical variables (sex, age, APOE genotype, Aβ42\\beta\_{42}, and pTau; missing values indicate unavailable biomarkers). The two panels show the top-5 support subjects retrieved by the multimodal TabPFN and the shortcut TabPFN, respectively. Bar length represents the normalized attention weight within each query, and colors denote diagnostic class (CN, MCI, and AD). Subject identifiers are anonymized (Snn), and ages above 90 years are reported as 90+90+ in accordance with the ADNI Data Use Agreement.To assess the contribution of each component of M2PFN to the final performance, we conduct an ablation study, reported in Table [3](https://arxiv.org/html/#S4.T3 "Table 3 ‣ 4.4 Classification on ADNI ‣ 4 Experiments ‣ M2PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer’s Disease"). The disentangled alignment module consistently improves both predictive performance and training stability, with its removal causing a modest but significant reduction in AUC (p<0.05p<0.05). In contrast, the architectural designs contribute more substantially. End-to-end optimization enables gradients from the frozen ICL engine to guide multimodal representation learning, and jointly removing end-to-end optimization and representation alignment leads to a much larger performance degradation than removing either component alone, indicating that the two are complementary. The frozen TabPFN shortcut further encourages the multimodal branch to learn complementary information beyond what is already captured by the tabular features, leading to richer multimodal representations and better performance. Finally, replacing the frozen TabPFN heads with trainable MLP classifiers produces the largest performance drop, demonstrating that preserving TabPFN’s pretrained in-context learning capabilities, rather than a conventional parametric classifier, is the largest source of M2PFN’s performance gain. 出处: M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease（arXiv）
