用少量代表性数据高效比对脑功能连接模型，提升神经科学可重复性。
Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set Selection
- 基于结构感知的对比学习，自动筛选能保持模型排名顺序的小样本集。
- 仅用10%数据即保留真实排序，排名一致性比现有方法高23.2%。
- 适合需要大规模模型评估的计算神经科学与医学影像研究者。
在大规模fMRI数据上对数百种功能连接（FC）建模方法进行基准测试对可重复神经科学研究至关重要。然而，模型与数据组合的组合爆炸使全面评估计算成本过高，难以成为常规预分析步骤。为此，我们重新定义了FC基准测试问题：选择一个小型、具有代表性的核心集，其唯一目的是保持各类FC算子的相对性能排名。我们将此形式化为保持排名的子集选择问题，并提出结构感知对比学习核心集选择（SCLCS），一种自监督框架用于生成此类核心集。SCLCS首先使用自适应Transformer学习每个样本的独特FC结构；随后引入新颖的结构扰动评分（SPS），量化训练过程中所学结构的稳定性，识别出代表基础连接原型的样本；最后，在通过top-k排名识别稳定样本的基础上，进一步采用密度均衡采样策略作为必要修正，以促进多样性，确保最终核心集兼具结构鲁棒性与分布代表性。在大规模REST-meta-MDD数据集上，SCLCS仅用10%数据即可保留真实模型排名，其排名一致性（nDCG@k）相比最先进（SOTA）核心集选择方法最高提升23.2%。据我们所知，这是首个将核心集选择正式应用于FC算子基准测试的工作，使大规模算子比较成为计算神经科学中可行且不可或缺的一环。代码已公开于https://github.com/lzhan94swu/SCLCS。
原文摘要 · Abstract (English)
Benchmarking the hundreds of functional connectivity (FC) modeling methods on large-scale fMRI datasets is critical for reproducible neuroscience. However, the combinatorial explosion of model-data pairings makes exhaustive evaluation computationally prohibitive, preventing such assessments from becoming a routine pre-analysis step. To break this bottleneck, we reframe the challenge of FC benchmarking by selecting a small, representative core-set whose sole purpose is to preserve the relative performance ranking of FC operators. We formalize this as a ranking-preserving subset selection problem and propose Structure-aware Contrastive Learning for Core-set Selection (SCLCS), a self-supervised framework to select these core-sets. SCLCS first uses an adaptive Transformer to learn each sample's unique FC structure. It then introduces a novel Structural Perturbation Score (SPS) to quantify the stability of these learned structures during training, identifying samples that represent foundational connectivity archetypes. Finally, while SCLCS identifies stable samples via a top-k ranking, we further introduce a density-balanced sampling strategy as a necessary correction to promote diversity, ensuring the final core-set is both structurally robust and distributionally representative. On the large-scale REST-meta-MDD dataset, SCLCS preserves the ground-truth model ranking with just 10% of the data, outperforming state-of-the-art (SOTA) core-set selection methods by up to 23.2% in ranking consistency (nDCG@k). To our knowledge, this is the first work to formalize core-set selection for FC operator benchmarking, thereby making large-scale operators comparisons a feasible and integral part of computational neuroscience. Code is publicly available on https://github.com/lzhan94swu/SCLCS
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。