Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set Selection

2026-02-05

AI Summary

This study addresses the prohibitive computational cost of benchmarking large-scale fMRI functional connectivity models, which arises from the combinatorial explosion of model–data configurations and hinders routine evaluation. To overcome this challenge, the work formalizes core-set selection as an order-preserving subset selection problem and introduces a structure-aware subset selection strategy that jointly optimizes structural stability and distributional diversity to construct a small yet representative data subset capable of preserving the true model performance ranking. The proposed method leverages a self-supervised, structure-aware contrastive learning framework (SCLCS), integrating an adaptive Transformer, a structural perturbation scoring (SPS) mechanism, and density-balanced sampling. Evaluated on the REST-meta-MDD dataset, the approach accurately maintains the ground-truth model ranking using only 10% of the data, achieving up to a 23.2% improvement in nDCG@k over the current state-of-the-art.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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

Problem

• functional connectivity
• benchmarking
• core-set selection
• fMRI
• computational neuroscience

Innovation

• core-set selection
• functional connectivity
• structure-aware contrastive learning
• Structural Perturbation Score
• ranking preservation