mlsanityData to 14 Oct 2026

BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait Prediction

arXiv 2511.05630 ↗First posted 7 Nov 2025q-bio.NC cs.AIcited by 0

On the map: Mixture-of-experts → Medical and biomedical MoE

Abstract (arXiv)

Functional and structural connectivity (FC/SC) are key multimodal biomarkers for brain analysis, yet their clinical utility is hindered by costly acquisition, complex preprocessing, and frequent missing modalities. Existing foundation models either process single modalities or lack explicit mechanisms for cross-modal and cross-scale consistency. We propose BrainCSD, a hierarchical mixture-of-experts (MoE) foundation model that jointly synthesizes FC/SC biomarkers and supports downstream decoding tasks (diagnosis and prediction). BrainCSD features three neuroanatomically grounded components: (1) a ROI-specific MoE that aligns regional activations from canonical networks (e.g., DMN, FPN) with a global atlas via contrastive consistency; (2) a Encoding-Activation MOE that models dynamic cross-time/gradient dependencies in fMRI/dMRI; and (3) a network-aware refinement MoE that enforces structural priors and symmetry at individual and population levels. Evaluated on the datasets under complete and missing-modality settings, BrainCSD achieves SOTA results: 95.6% accuracy for MCI vs. CN classification without FC, low synthesis error (FC RMSE: 0.038; SC RMSE: 0.006), brain age prediction (MAE: 4.04 years), and MMSE score estimation (MAE: 1.72 points). Code is available in hrefhttps://github.com/SXR3015/BrainCSDBrainCSD

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts. Builds on 5 of its 52 references that are in the map. First posted on arXiv 7 Nov 2025.

Builds on

5 of 52 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025BrainNet-MoE: Brain-Inspired Mixture-of-Experts Learning for Neurological Disease Identification5 Mar

Other references · 4

  1. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  2. 2022DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scalecited by 404
  3. 2024Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Expertscited by 108
  4. 2024BrainMass: Advancing Brain Network Analysis for Diagnosis with Large-scale Self-Supervised Learningcited by 32

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Structural-Functional Brain Connectivity Generation via Multimodal Hypergraph-based Flow Matching
  2. 2026M3D-BFS: a Multi-stage Dynamic Fusion Strategy for Sample-Adaptive Multi-Modal Brain Network Analysis
  3. 2023BrainNetDiff: Generative AI Empowers Brain Network Generation via Multimodal Diffusion Model
  4. 2026FPED: A Functional-Network Prior-Guided Mixture-of-Experts Framework for Interpretable Brain Decoding
  5. 2025Bridging Foundation Models and Efficient Architectures: A Modular Brain Imaging Framework with Local Masking and Pretrained Representation Learning
  6. 2026Navigating Hierarchy: Hyperbolic Learning on Brain Graphs for Disorder Diagnosis
  7. 2026Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay
  8. 2018Mixture of Regression Experts in fMRI Encoding