BrainLinear: A Linear Model for Brain Network Analysis in Sparse Tangent Subspaces

• URL: http://arxiv.org/abs/2608.15266v1
• Date: Sat, 15 Aug 2026 14:57:48 GMT
• Title: BrainLinear: A Linear Model for Brain Network Analysis in Sparse Tangent Subspaces
• Abstract summary: BrainLinear is a lightweight framework for mining disease-discriminative connectome patterns.<n>It matches or exceeds strong GNN and Transformer baselines at a fraction of their cost.<n>It reduces runtime and peak GPU memory by $84.0%$ and $68.4%$ relative to the closest baseline in AUC.
• Score: 26.68112538190199
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Functional connectome analysis examines brain-region interactions to understand and identify disorders such as autism spectrum disorder and Alzheimer's disease. Existing methods typically use GNNs and Transformers to model the full functional connectivity matrix. However, processing tens of thousands of connections introduces redundancy and noise, increases computational cost, and limits connection-level interpretability. This raises a central question: do we really need complex interaction modeling, or is identifying a small set of disease-relevant connectivity patterns sufficient? To answer this question, we propose BrainLinear, a lightweight geometry-aware framework for mining disease-discriminative connectome patterns. BrainLinear first maps each functional connectivity matrix to a shared tangent space centered at the Fréchet mean of the training set, capturing subject-specific deviations while respecting matrix geometry. It then scores each ROI-pair tangent direction by its classification contribution and disease--control difference, retaining Top-$K$ directions as a compact representation. Finally, a shallow multilayer perceptron performs classification on the selected representation. Experiments on ABIDE and ADNI show that BrainLinear matches or exceeds strong GNN and Transformer baselines at a fraction of their cost: it improves AUC and ACC over the best baseline for each metric by up to $3.54$ and $1.39$ percentage points, while reducing runtime and peak GPU memory by $84.0\%$ and $68.4\%$ relative to the closest baseline in AUC. The selected directions are directionally consistent with between-group displacements and organized across major functional systems, supporting connection-level interpretation.

Related papers

• Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons [27.855778669417592]
  Cortical neurons are complex, multi-timescale processors wired into recurrent circuits.<n>Machine learning predominantly builds models extremely simple units, a default inherited from early neural-network theory.<n>We introduce the ELM Network, whose recurrent layer is built from Expressive Memory (ELM) neurons.
  arXiv  Detail & Related papers  (2026-05-12T12:29:33Z)
• Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing [72.45257414889478]
  We aim to reduce human workload by predicting connectivity between over-segmented neuron pieces. We first construct a dataset, named FlyTracing, that contains millions of pairwise connections of segments expanding the whole fly brain. We propose a novel connectivity-aware contrastive learning method to generate dense volumetric EM image embedding.
  arXiv  Detail & Related papers  (2024-01-05T19:45:12Z)
• Towards understanding neural collapse in supervised contrastive learning with the information bottleneck method [26.874007846077884]
  Neural collapse describes the geometry of activation in the final layer of a deep neural network when it is trained beyond performance plateaus. We demonstrate that neural collapse leads to good generalization specifically when it approaches an optimal IB solution of the classification problem.
  arXiv  Detail & Related papers  (2023-05-19T18:41:17Z)
• Brain Network Transformer [13.239896897835191]
  We study Transformer-based models for brain network analysis. Driven by the unique properties of data, we model brain networks as graphs with nodes of fixed size and order. We re-standardize the evaluation pipeline on the only one publicly available large-scale brain network dataset of ABIDE.
  arXiv  Detail & Related papers  (2022-10-13T02:30:06Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Deep Graph Normalizer: A Geometric Deep Learning Approach for Estimating Connectional Brain Templates [0.0]
  A connectional brain template (CBT) is a normalized graph-based representation of a population of brain networks. Deep Graph Normalizer (DGN) is the first geometric deep learning architecture for normalizing a population of MVBNs. DGN learns how to fuse multi-view brain networks while capturing non-linear patterns across subjects.
  arXiv  Detail & Related papers  (2020-12-28T08:01:49Z)
• Comparisons among different stochastic selection of activation layers for convolutional neural networks for healthcare [77.99636165307996]
  We classify biomedical images using ensembles of neural networks. We select our activations among the following ones: ReLU, leaky ReLU, Parametric ReLU, ELU, Adaptive Piecewice Linear Unit, S-Shaped ReLU, Swish, Mish, Mexican Linear Unit, Parametric Deformable Linear Unit, Soft Root Sign.
  arXiv  Detail & Related papers  (2020-11-24T01:53:39Z)
• Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge Computing [113.52575069030192]
  Big data, including applications with high security requirements, are often collected and stored on multiple heterogeneous devices, such as mobile devices, drones and vehicles. Due to the limitations of communication costs and security requirements, it is of paramount importance to extract information in a decentralized manner instead of aggregating data to a fusion center. We consider the problem of learning model parameters in a multi-agent system with data locally processed via distributed edge nodes. A class of mini-batch alternating direction method of multipliers (ADMM) algorithms is explored to develop the distributed learning model.
  arXiv  Detail & Related papers  (2020-10-02T10:41:59Z)
• Multi-View Brain HyperConnectome AutoEncoder For Brain State Classification [0.0]
  We propose a new strategy to build a hyperconnectome for each brain view based on nearest neighbour algorithm. We also design a hyperconnectome autoencoder framework which operates directly on the multi-view hyperconnectomes. Our experiments showed that the learned embeddings by HCAE yield to better results for brain state classification.
  arXiv  Detail & Related papers  (2020-09-24T08:51:44Z)
• Context-Aware Refinement Network Incorporating Structural Connectivity Prior for Brain Midline Delineation [50.868845400939314]
  We propose a context-aware refinement network (CAR-Net) to refine and integrate the feature pyramid representation generated by the UNet. For keeping the structural connectivity of the brain midline, we introduce a novel connectivity regular loss. The proposed method requires fewer parameters and outperforms three state-of-the-art methods in terms of four evaluation metrics.
  arXiv  Detail & Related papers  (2020-07-10T14:01:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.