# Progressive Self-Supervised Learning with Individualized Community Assignment for Brain Network Analysis

arXiv: https://arxiv.org/abs/2606.29695 · HTML: https://mlsanity.com/paper/2606.29695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BrainMass: Advancing Brain Network Analysis for Diagnosis with Large-scale Self-Supervised Learning](https://mlsanity.com/paper/2403.01433/) (2024)
- [Community-Aware Transformer for Autism Prediction in fMRI Connectome](https://mlsanity.com/paper/2307.10181/) (2023)
- [P2OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering](https://mlsanity.com/paper/2401.09266/) (2024)
- [EAG-RS: A Novel Explainability-guided ROI-Selection Framework for ASD Diagnosis via Inter-regional Relation Learning](https://mlsanity.com/paper/2310.03404/) (2023)
- [Advancing Brain Imaging Analysis Step-by-step via Progressive Self-paced Learning](https://mlsanity.com/paper/2407.16128/) (2024)
- [Hierarchical Characterization of Brain Dynamics via State Space-based Vector Quantization](https://mlsanity.com/paper/2506.22952/) (2025)
- [BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysis](https://mlsanity.com/paper/2511.17604/) (2025)

## Abstract (arXiv)

Brain networks exhibit a modular community structure that varies across individuals and neurological conditions. However, existing self-supervised learning (SSL) methods often overlook this heterogeneity, relying on generic masking strategies that fail to capture subject-specific functional organization. We propose BrainPICM, a self-supervised framework for brain network analysis via progressive individualized community aware masking. BrainPICM formulates ROI-to-community mapping as a progressive unbalanced optimal transport process, yielding soft assignments and per-ROI confidence scores. Guided by these confidence estimates, a curriculum-style masking strategy gradually incorporates low-confidence, potentially pathological regions into training, enabling the model to learn both stable modular structures and individual variations. Additionally, a deviation-aware aggregation module quantifies functional reorganization by measuring mass redistribution relative to a population template, enhancing interpretability and downstream prediction. Experiments on three fMRI datasets (ABIDE-I, ADHD-200, ADNI) show that BrainPICM consistently outperforms state-of-the-art supervised and SSL methods in diagnostic accuracy, indicating that explicitly injecting modular community structure into masked modeling yields more functionally consistent and generalizable representations. The source code for this approach will be released at https://github.com/Hrychen7/BrainPICM.