Unified Generative Latent Representation for Functional Brain Graphs

• URL: http://arxiv.org/abs/2511.04539v1
• Date: Thu, 06 Nov 2025 16:52:49 GMT
• Title: Unified Generative Latent Representation for Functional Brain Graphs
• Authors: Subati Abulikemu, Tiago Azevedo, Michail Mamalakis, John Suckling,
• Abstract summary: Functional brain graphs are often characterized with separate graph-theoretic or spectral descriptors.<n>We estimate this unified graph representation through a graph transformer autoencoder with latent diffusion.<n>From the diffusion modeled distribution, we were able to sample biologically plausible and structurally grounded synthetic dense graphs.
• Score: 0.341987335587885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Functional brain graphs are often characterized with separate graph-theoretic or spectral descriptors, overlooking how these properties covary and partially overlap across brains and conditions. We anticipate that dense, weighted functional connectivity graphs occupy a low-dimensional latent geometry along which both topological and spectral structures display graded variations. Here, we estimated this unified graph representation and enabled generation of dense functional brain graphs through a graph transformer autoencoder with latent diffusion, with spectral geometry providing an inductive bias to guide learning. This geometry-aware latent representation, although unsupervised, meaningfully separated working-memory states and decoded visual stimuli, with performance further enhanced by incorporating neural dynamics. From the diffusion modeled distribution, we were able to sample biologically plausible and structurally grounded synthetic dense graphs.

Related papers

• Heterogeneous Graph Contrastive Learning with Spectral Augmentation [15.231689595121553]
  This paper introduces a spectral-enhanced graph contrastive learning model (SHCL) for the first time in heterogeneous graph neural networks. The proposed model learns an adaptive topology augmentation scheme through the heterogeneous graph itself. Experimental results on multiple real-world datasets demonstrate substantial advantages of the proposed model.
  arXiv  Detail & Related papers  (2024-06-30T14:20:12Z)
• Improving embedding of graphs with missing data by soft manifolds [51.425411400683565]
  The reliability of graph embeddings depends on how much the geometry of the continuous space matches the graph structure. We introduce a new class of manifold, named soft manifold, that can solve this situation. Using soft manifold for graph embedding, we can provide continuous spaces to pursue any task in data analysis over complex datasets.
  arXiv  Detail & Related papers  (2023-11-29T12:48:33Z)
• Supercharging Graph Transformers with Advective Diffusion [28.40109111316014]
  This paper proposes Advective Diffusion Transformer (AdvDIFFormer), a physics-inspired graph Transformer model designed to address this challenge.<n>We show that AdvDIFFormer has provable capability for controlling generalization error with topological shifts.<n> Empirically, the model demonstrates superiority in various predictive tasks across information networks, molecular screening and protein interactions.
  arXiv  Detail & Related papers  (2023-10-10T08:40:47Z)
• Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
  Contrastive learning has emerged as a premier method for learning representations with or without supervision. Recent studies have shown its utility in graph representation learning for pre-training. We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
  arXiv  Detail & Related papers  (2023-02-06T16:26:29Z)
• Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs [16.88394293874848]
  We use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs. By considering a hierarchy of increasingly general sheaves, we study how the ability of the sheaf diffusion process to achieve linear separation of the classes in the infinite time limit expands. We prove that when the sheaf is non-trivial, discretised parametric diffusion processes have greater control than GNNs over their behaviour.
  arXiv  Detail & Related papers  (2022-02-09T17:25:02Z)
• Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification [50.899576891296235]
  Convolutional neural networks have been widely applied to hyperspectral image classification. Recent methods attempt to address this issue by performing graph convolutions on spatial topologies.
  arXiv  Detail & Related papers  (2021-06-26T06:24:51Z)
• Directed Graph Embeddings in Pseudo-Riemannian Manifolds [0.0]
  We show that general directed graphs can be effectively represented by an embedding model that combines three components. We demonstrate the representational capabilities of this method by applying it to the task of link prediction.
  arXiv  Detail & Related papers  (2021-06-16T10:31:37Z)
• Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference [48.63194907060615]
  We build off of semi-implicit graph variational auto-encoders to capture higher-order statistics in a low-dimensional graph latent representation. We incorporate hyperbolic geometry in the latent space through a Poincare embedding to efficiently represent graphs exhibiting hierarchical structure.
  arXiv  Detail & Related papers  (2020-10-31T05:48:34Z)
• GraphOpt: Learning Optimization Models of Graph Formation [72.75384705298303]
  We propose an end-to-end framework that learns an implicit model of graph structure formation and discovers an underlying optimization mechanism. The learned objective can serve as an explanation for the observed graph properties, thereby lending itself to transfer across different graphs within a domain. GraphOpt poses link formation in graphs as a sequential decision-making process and solves it using maximum entropy inverse reinforcement learning algorithm.
  arXiv  Detail & Related papers  (2020-07-07T16:51:39Z)
• Graph Laplacians, Riemannian Manifolds and their Machine-Learning [2.258160413679475]
  We apply some of the latest techniques in data science such as supervised and unsupervised machine-learning and topological data analysis to the Wolfram database of some 8000 finite graphs. We find that neural classifiers, regressors and networks can perform, with high efficiently and accuracy, a multitude of tasks ranging from recognizing graph Ricci-flatness, to predicting the spectral gap, to detecting the presence of Hamiltonian cycles.
  arXiv  Detail & Related papers  (2020-06-30T09:16:56Z)
• Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings [71.20283285671461]
  We propose a geometric scattering autoencoder (GSAE) network for learning such graph embeddings. Our embedding network first extracts rich graph features using the recently proposed geometric scattering transform. We show that GSAE organizes RNA graphs both by structure and energy, accurately reflecting bistable RNA structures.
  arXiv  Detail & Related papers  (2020-06-12T00:17:59Z)

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.