fMRI is a non-invasive technique for investigating brain activity, offering high-resolution insights into neural processes. Understanding and decoding cognitive brain states from fMRI depends on how functional interactions are represented. We propose an ensemble-based graph representation in which each edge weight encodes state evidence as the difference between posterior probabilities of two states, estimated by an ensemble of edge-wise probabilistic classifiers from simple pairwise time-series features. We evaluate the method on seven task-fMRI paradigms from the Human Connectome Project, performing binary classification within each paradigm. Using compact node summaries (mean incident edge weights) and logistic regression, we obtain average accuracies of 97.07-99.74 %. We further compare ensemble graphs with conventional correlation graphs using the same graph neural network classifier; ensemble graphs consistently yield higher accuracy (88.00-99.42 % vs 61.86-97.94 % across tasks). Because edge weights have a probabilistic, state-oriented interpretation, the representation supports connection- and region-level interpretability and can be extended to multiclass decoding, regression, other neuroimaging modalities, and clinical classification.

翻译：功能磁共振成像（fMRI）是一种研究大脑活动的非侵入性技术，为神经过程提供了高分辨率的观测手段。从fMRI数据中理解和解码认知脑状态，关键在于如何表征功能交互作用。本文提出一种基于集成学习的图表示方法，其中每条边的权重通过集成边级概率分类器从简单的成对时间序列特征中估计两个状态的后验概率之差，以此编码状态证据。我们在人类连接组计划的七个任务fMRI范式上评估该方法，并在每个范式内进行二分类。通过使用紧凑的节点摘要（平均入射边权重）和逻辑回归，我们获得了97.07-99.74%的平均准确率。我们进一步使用相同的图神经网络分类器，将集成图与传统相关图进行比较；集成图在所有任务中均取得更高的准确率（88.00-99.42% vs 61.86-97.94%）。由于边权重具有概率化、面向状态的解释性，该表示方法支持连接层面和区域层面的可解释性，并可扩展至多类解码、回归、其他神经影像模态及临床分类任务。