# Divergence unveils further distinct phenotypic traits of human brain connectomics fingerprint

## TL;DR

This paper introduces a new method for analyzing brain connectivity patterns that improves individual identification accuracy across different brain scans and resolutions.

## Contribution

The Alpha-Z Bures-Wasserstein divergence provides a geometry-aware, parameter-free framework for functional connectome comparison.

## Key findings

- Alpha-Z achieves higher identification rates in rank-deficient functional connectome regimes.
- The method preserves performance across different parcellation schemes and scan conditions.
- It requires no regularization tuning and works well with short scan durations.

## Abstract

The accurate identification of individuals from functional connectomes (FCs) is central to individualized neuro/psychiatric assessment. Traditional metrics (Pearson and Euclidean) fail to capture the non-Euclidean geometry of FCs, and geodesic metrics (affine-invariant and Log-Euclidean) require task- and scale-specific regularization and degrade in high-dimensional settings. To address these challenges, we propose the Alpha-Z Bures-Wasserstein divergence, a geometry-aware divergence for FC comparison that operates effectively without meticulous parameter tuning. Across Human Connectome Project tasks, scan lengths, and spatial resolutions, we benchmark Alpha-Z against classical and state-of-the-art manifold-based distances and quantify how varying regularization influences geodesic performance. Alpha-Z yields consistently higher identification rates, with pronounced advantages in rank-deficient regimes, and preserves performance across parcellations and conditions. We further verify generalization across resting-state and task fMRI under multiple parcellation schemes. These results position Alpha-Z as a reliable, robust, and scalable framework for functional connectivity analysis, improving sensitivity to cognitive and behavioral patterns and offering strong potential for individualized clinical neuroscience.

•Divergence enhances FC fingerprinting across tasks and parcellations•Robust to high-dimensional, rank-deficient FCs; no regularization tuning required•Preserves network-level identifiability consistently across spatial scales•Achieves near-ceiling ID with short scans; validated against null models

Divergence enhances FC fingerprinting across tasks and parcellations

Robust to high-dimensional, rank-deficient FCs; no regularization tuning required

Preserves network-level identifiability consistently across spatial scales

Achieves near-ceiling ID with short scans; validated against null models

Neuroscience; Cognitive neuroscience; Techniques in neuroscience