[论文] BrainTaskonomy: Learning How to Pretrain and What to Transfer in fMRI Foundation Models

论文概要

研究领域: CV 作者: Junfeng Xia, Wenhao Ye, Junxiang Zhang, Jiayu Zuo, Mo Wang, Quanying Liu 发布时间: 2026-09-09 arXiv: 2609.10518

中文摘要

fMRI基础模型越来越多地聚合跨脑状态、队列和采集设置的异构数据，但预训练域通常被视为扁平混合，下游任务独立适配。本文研究是否可以通过测量的学习关系来组织这两个阶段而无需修改主干网络。预训练期间，轻量级Brain-DiT代理估计十个fMRI域的难度和定向促进，产生优先级引导的累积域课程，结合高到低噪声时间步调度和联合巩固。适配期间，跨十五个任务的受控一阶和高阶迁移构建有向任务学(taskonomy)，预算整数规划(BIP)从中选择直接监督的源任务和目标特定路径。联合优先级域和高到低时间步课程相比两个维度的均匀采样，v-NMSE、PSD-NMSE和FC-MSE分别降低6.5%、16.3%和10.5%，在六个域内和域外任务上表现出强大的下游性能。

原文摘要

fMRI foundation models increasingly aggregate heterogeneous data across brain states, cohorts, and acquisition settings, yet pretraining domains are commonly treated as a flat mixture and downstream tasks are adapted independently. We study whether measured learning relations can organize both stages without modifying the backbone. During pretraining, a lightweight Brain-DiT proxy estimates difficulty and directed facilitation across ten fMRI domains, yielding a priority-guided cumulative domain curriculum combined with high-to-low-noise timestep scheduling and joint consolidation. During adaptation, controlled first- and higher-order transfer across fifteen tasks constructs a directed taskonomy, from which budgeted integer programming (BIP) selects directly supervised source tasks and target-specific routes. The joint priority-domain and high-to-low-timestep curriculum reduces v-NMSE, PSD-NMSE, and FC-MSE by 6.5%, 16.3%, and 10.5%, respectively, relative to uniform sampling over both dimensions, and shows strong downstream performance across six in- and out-of-domain tasks. The taskonomy reveals asymmetric, target-dependent transfer, while exploratory sealed-test evaluation shows larger descriptive gains for BIP policies when higher-order route spaces are available than for matched random controls. Together, these findings support organizing fMRI pretraining and adaptation by measured learning relations rather than treating domains and tasks as independent flat sets.

---

*自动采集于 2026-09-11*

#论文 #arXiv #CV #小凯