Torsion in Persistent Homology and Neural Networks

• URL: http://arxiv.org/abs/2506.03049v2
• Date: Wed, 09 Jul 2025 10:38:34 GMT
• Title: Torsion in Persistent Homology and Neural Networks
• Authors: Maria Walch,
• Abstract summary: We show that torsion can be lost during encoding, altered in the latent space, and in many cases, not reconstructed by standard decoders.<n>Our findings reveal key limitations of field-based approaches and underline the need for architectures or loss terms that preserve torsional information.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We explore the role of torsion in hybrid deep learning models that incorporate topological data analysis, focusing on autoencoders. While most TDA tools use field coefficients, this conceals torsional features present in integer homology. We show that torsion can be lost during encoding, altered in the latent space, and in many cases, not reconstructed by standard decoders. Using both synthetic and high-dimensional data, we evaluate torsion sensitivity to perturbations and assess its recoverability across several autoencoder architectures. Our findings reveal key limitations of field-based approaches and underline the need for architectures or loss terms that preserve torsional information for robust data representation.

Related papers

• Enhancing anomaly detection with topology-aware autoencoders [0.0]
  Autoencoders provide a signal-agnostic approach but are limited by the topology of their latent space.<n>We construct autoencoders with spherical ($Sn$), product ($S2 otimes S2$), and projective ($mathbbRP2$) latent spaces.<n>Applying our approach to simulated hadronic top-quark decays, we show that latent spaces with appropriate topological constraints enhance sensitivity and robustness in detecting anomalous events.
  arXiv  Detail & Related papers  (2025-02-14T13:50:46Z)
• An Automated Data Mining Framework Using Autoencoders for Feature Extraction and Dimensionality Reduction [10.358417199718462]
  This study proposes an automated data mining framework based on autoencoders and experimentally verifies its effectiveness in feature extraction and data dimensionality reduction.<n>Through the encoding-decoding structure, the autoencoder can capture the data's potential characteristics and achieve noise reduction and anomaly detection.<n>In the future, with the advancement of deep learning and big data technology, the autoencoder method combined with a generative adversarial network (GAN) or graph neural network (GNN) is expected to be more widely used in the fields of complex data processing, real-time data analysis and intelligent decision-making.
  arXiv  Detail & Related papers  (2024-12-03T07:04:10Z)
• Remote sensing framework for geological mapping via stacked autoencoders and clustering [0.15833270109954137]
  We present an unsupervised machine learning-based framework for processing remote sensing data. We use Landsat 8, ASTER, and Sentinel-2 datasets to evaluate the framework for geological mapping of the Mutawintji region in Australia. Our results reveal that the framework produces accurate and interpretable geological maps, efficiently discriminating rock units.
  arXiv  Detail & Related papers  (2024-04-02T09:15:32Z)
• Ensuring Topological Data-Structure Preservation under Autoencoder Compression due to Latent Space Regularization in Gauss--Legendre nodes [0.0]
  We prove that regularised autoencoders ensure a one-to-one re-embedding of the initial data manifold to its latent representation. This observation extends through the classic FashionMNIST dataset up to real world encoding problems for MRI brain scans.
  arXiv  Detail & Related papers  (2023-09-15T07:58:26Z)
• ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction [55.30913411696375]
  We propose an Asymmetric Receptive Field Autoencoder (ARFA) model, which introduces corresponding sizes of receptive field modules. In the encoder, we present large kernel module for globaltemporal feature extraction. In the decoder, we develop a small kernel module for localtemporal reconstruction. We construct the RainBench, a large-scale radar echo dataset for precipitation prediction, to address the scarcity of meteorological data in the domain.
  arXiv  Detail & Related papers  (2023-09-01T07:55:53Z)
• From NeurODEs to AutoencODEs: a mean-field control framework for width-varying Neural Networks [68.8204255655161]
  We propose a new type of continuous-time control system, called AutoencODE, based on a controlled field that drives dynamics. We show that many architectures can be recovered in regions where the loss function is locally convex.
  arXiv  Detail & Related papers  (2023-07-05T13:26:17Z)
• Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders [45.29194877564103]
  This work introduces a chart autoencoder with an asymmetric encoding-decoding process that can incorporate additional semi-supervised information such as class labels. We discuss the approximation power of such networks and derive a bound that essentially depends on the intrinsic dimension of the data manifold rather than the dimension of ambient space.
  arXiv  Detail & Related papers  (2022-08-22T19:58:03Z)
• Toward a Geometrical Understanding of Self-supervised Contrastive Learning [55.83778629498769]
  Self-supervised learning (SSL) is one of the premier techniques to create data representations that are actionable for transfer learning in the absence of human annotations. Mainstream SSL techniques rely on a specific deep neural network architecture with two cascaded neural networks: the encoder and the projector. In this paper, we investigate how the strength of the data augmentation policies affects the data embedding.
  arXiv  Detail & Related papers  (2022-05-13T23:24:48Z)
• Neural Distributed Source Coding [59.630059301226474]
  We present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. We evaluate our method on multiple datasets and show that our method can handle complex correlations and state-of-the-art PSNR.
  arXiv  Detail & Related papers  (2021-06-05T04:50:43Z)
• G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification [49.53651166356737]
  We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers. We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data.
  arXiv  Detail & Related papers  (2021-01-27T19:28:04Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)
• Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations [0.7614628596146599]
  We introduce an Encoded Prior Sliced Wasserstein AutoEncoder. An additional prior-encoder network learns an embedding of the data manifold. We show that the prior encodes the geometry underlying the data unlike conventional autoencoders.
  arXiv  Detail & Related papers  (2020-10-02T14:58:54Z)
• Deep Autoencoding Topic Model with Scalable Hybrid Bayesian Inference [55.35176938713946]
  We develop deep autoencoding topic model (DATM) that uses a hierarchy of gamma distributions to construct its multi-stochastic-layer generative network. We propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a downward generative model. The efficacy and scalability of our models are demonstrated on both unsupervised and supervised learning tasks on big corpora.
  arXiv  Detail & Related papers  (2020-06-15T22:22:56Z)

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.