Global graph features unveiled by unsupervised geometric deep learning

• URL: http://arxiv.org/abs/2503.05560v1
• Date: Fri, 07 Mar 2025 16:38:41 GMT
• Title: Global graph features unveiled by unsupervised geometric deep learning
• Authors: Mirja Granfors, Jesús Pineda, Blanca Zufiria Gerbolés, Joana B. Pereira, Carlo Manzo, Giovanni Volpe,
• Abstract summary: We introduce GAUDI (Graph Autoencoder Uncovering Descriptive Information), a novel geometric unsupervised deep learning framework.<n>GAUDI employs an innovative hourglass architecture with hierarchical pooling and upsampling layers, linked through skip connections to preserve connectivity information.<n>We demonstrate its power across multiple applications, including modeling small-world networks, characterizing assemblies from super-resolution microscopy, analyzing collective motion in the Vicsek model, and capturing age changes in brain connectivity.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graphs provide a powerful framework for modeling complex systems, but their structural variability makes analysis and classification challenging. To address this, we introduce GAUDI (Graph Autoencoder Uncovering Descriptive Information), a novel unsupervised geometric deep learning framework that captures both local details and global structure. GAUDI employs an innovative hourglass architecture with hierarchical pooling and upsampling layers, linked through skip connections to preserve essential connectivity information throughout the encoding-decoding process. By mapping different realizations of a system - generated from the same underlying parameters - into a continuous, structured latent space, GAUDI disentangles invariant process-level features from stochastic noise. We demonstrate its power across multiple applications, including modeling small-world networks, characterizing protein assemblies from super-resolution microscopy, analyzing collective motion in the Vicsek model, and capturing age-related changes in brain connectivity. This approach not only improves the analysis of complex graphs but also provides new insights into emergent phenomena across diverse scientific domains.

Related papers

• Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers [0.0]
  We reformulate the Transformer's attention mechanism as a graph operation. We introduce Sparse GIN-Attention, a fine-tuning approach that employs sparse GINs.
  arXiv  Detail & Related papers  (2025-01-04T22:30:21Z)
• Higher-Order Message Passing for Glycan Representation Learning [0.0]
  Graph Networks (GNNs) are deep learning models designed to process and analyze graph-structured data.<n>This work presents a new model architecture based on complexes and higher-order message passing to extract features from glycan structures into latent space representation.<n>We envision that these improvements will spur further advances in computational glycosciences and reveal the roles of glycans in biology.
  arXiv  Detail & Related papers  (2024-09-20T12:55:43Z)
• Hi-GMAE: Hierarchical Graph Masked Autoencoders [90.30572554544385]
  Hierarchical Graph Masked AutoEncoders (Hi-GMAE) Hi-GMAE is a novel multi-scale GMAE framework designed to handle the hierarchical structures within graphs. Our experiments on 15 graph datasets consistently demonstrate that Hi-GMAE outperforms 17 state-of-the-art self-supervised competitors.
  arXiv  Detail & Related papers  (2024-05-17T09:08:37Z)
• Integrating multiscale topology in digital pathology with pyramidal graph convolutional networks [0.10995326465245926]
  Graph convolutional networks (GCNs) have emerged as a powerful alternative to multiple instance learning with convolutional neural networks in digital pathology. Our proposed multi-scale GCN (MS-GCN) tackles this issue by leveraging information across multiple magnification levels in whole slide images. MS-GCN demonstrates superior performance over existing single-magnification GCN methods.
  arXiv  Detail & Related papers  (2024-03-22T09:48:50Z)
• Topological Pooling on Graphs [24.584372324701885]
  Graph neural networks (GNNs) have demonstrated a significant success in various graph learning tasks. We propose a novel topological pooling layer and witness complex-based topological embedding mechanism. We show that Wit-TopoPool significantly outperforms all competitors across all datasets.
  arXiv  Detail & Related papers  (2023-03-25T19:30:46Z)
• Convolutional Learning on Multigraphs [153.20329791008095]
  We develop convolutional information processing on multigraphs and introduce convolutional multigraph neural networks (MGNNs) To capture the complex dynamics of information diffusion within and across each of the multigraph's classes of edges, we formalize a convolutional signal processing model. We develop a multigraph learning architecture, including a sampling procedure to reduce computational complexity. The introduced architecture is applied towards optimal wireless resource allocation and a hate speech localization task, offering improved performance over traditional graph neural networks.
  arXiv  Detail & Related papers  (2022-09-23T00:33:04Z)
• Semi-Supervised Deep Learning for Multiplex Networks [20.671777884219555]
  Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations. We present a novel semi-supervised approach for structure-aware representation learning on multiplex networks.
  arXiv  Detail & Related papers  (2021-10-05T13:37:43Z)
• Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification [63.56018768401328]
  We propose a Multi-level Graph Convolutional Network (GCN) with Automatic Graph Learning method (MGCN-AGL) for HSI classification. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions. Our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level.
  arXiv  Detail & Related papers  (2020-09-19T09:26:20Z)
• Graph signal processing for machine learning: A review and new perspectives [57.285378618394624]
  We review a few important contributions made by GSP concepts and tools, such as graph filters and transforms, to the development of novel machine learning algorithms. We discuss exploiting data structure and relational priors, improving data and computational efficiency, and enhancing model interpretability. We provide new perspectives on future development of GSP techniques that may serve as a bridge between applied mathematics and signal processing on one side, and machine learning and network science on the other.
  arXiv  Detail & Related papers  (2020-07-31T13:21:33Z)
• Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification [50.83222170524406]
  We study the intrinsic difficulty in graph classification under the unified concept of resolution dilemmas'' We propose SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling.
  arXiv  Detail & Related papers  (2020-06-29T01:01:42Z)
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning [74.05478502080658]
  This paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. The proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.
  arXiv  Detail & Related papers  (2020-03-15T02:33:21Z)

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.