Variational decomposition autoencoding improves disentanglement of latent representations

• URL: http://arxiv.org/abs/2601.06844v1
• Date: Sun, 11 Jan 2026 10:16:34 GMT
• Title: Variational decomposition autoencoding improves disentanglement of latent representations
• Authors: Ioannis Ziogas, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis,
• Abstract summary: We introduce variational decomposition autoencoding (VDA), a framework that extends VAEs by incorporating a strong structural bias toward signal decomposition.<n>VDA is instantiated through variational decomposition autoencoders (DecVAEs), i.e., encoder-only neural networks that combine a signal decomposition model, a contrastive self-supervised task, and variational prior approximation.<n>We demonstrate the effectiveness of DecVAEs on simulated data and three publicly available scientific datasets, spanning speech recognition, dysarthria severity evaluation, and emotional speech classification.
• Score: 14.3216921403324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn disentangled and interpretable representations is critical for uncovering latent generative mechanisms. Traditional approaches to unsupervised representation learning, including variational autoencoders (VAEs), often struggle to capture the temporal and spectral diversity inherent in such data. Here we introduce variational decomposition autoencoding (VDA), a framework that extends VAEs by incorporating a strong structural bias toward signal decomposition. VDA is instantiated through variational decomposition autoencoders (DecVAEs), i.e., encoder-only neural networks that combine a signal decomposition model, a contrastive self-supervised task, and variational prior approximation to learn multiple latent subspaces aligned with time-frequency characteristics. We demonstrate the effectiveness of DecVAEs on simulated data and three publicly available scientific datasets, spanning speech recognition, dysarthria severity evaluation, and emotional speech classification. Our results demonstrate that DecVAEs surpass state-of-the-art VAE-based methods in terms of disentanglement quality, generalization across tasks, and the interpretability of latent encodings. These findings suggest that decomposition-aware architectures can serve as robust tools for extracting structured representations from dynamic signals, with potential applications in clinical diagnostics, human-computer interaction, and adaptive neurotechnologies.

Related papers

• RAICL: Retrieval-Augmented In-Context Learning for Vision-Language-Model Based EEG Seizure Detection [12.189806103703887]
  We propose a paradigm shift from conventional signal-based decoding by leveraging large-scale vision-language models (VLMs) to analyze EEG waveform plots.<n>To address the inherent non-stationarity of EEG signals, we introduce a Retrieval-Augmented In-Context Learning (RAICL) approach.
  arXiv  Detail & Related papers  (2026-01-25T13:58:31Z)
• BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Classification [1.3909285316906435]
  BEAT-Net is a Biomimetic ECG Analysis with Tokenization framework.<n>It decomposes cardiac physiology through specialized encoders that extract local beat morphology.<n>It exhibits exceptional data efficiency, recovering fully supervised performance using only 30 to 35 percent of annotated data.
  arXiv  Detail & Related papers  (2026-01-12T08:37:47Z)
• A Novel Data Augmentation Strategy for Robust Deep Learning Classification of Biomedical Time-Series Data: Application to ECG and EEG Analysis [2.355460994057843]
  This study proposes a novel and unified deep learning framework that achieves state-of-the-art performance across different signal types.<n>Unlike prior work, we scientifically increase signal complexity to achieve future-reaching capabilities, which resulted in the best predictions.<n>The architecture requires 130 MB of memory and processes each sample in 10 ms, suggesting suitability for deployment on low-end or wearable devices.
  arXiv  Detail & Related papers  (2025-07-16T21:38:10Z)
• Clinical NLP with Attention-Based Deep Learning for Multi-Disease Prediction [44.0876796031468]
  This paper addresses the challenges posed by the unstructured nature and high-dimensional semantic complexity of electronic health record texts.<n>A deep learning method based on attention mechanisms is proposed to achieve unified modeling for information extraction and multi-label disease prediction.
  arXiv  Detail & Related papers  (2025-07-02T07:45:22Z)
• Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction [20.1863553357121]
  Current deep learning architectures for remote sensing are fundamentally rigid.<n>We introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling.<n> STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands.<n>It unifies various dense prediction tasks and diverse semantic class predictions.
  arXiv  Detail & Related papers  (2025-05-18T07:39:17Z)
• Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics with Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis [1.170167705525779]
  This paper proposes a novel visual analytics framework that integrates two generative AI models, Temporal Fusion Transformer (TFT) and Variational Autoencoders (VAEs)<n>It reduces complex patterns into lower-dimensional latent spaces and visualizes them in 2D using dimensionality reduction techniques such as PCA, t-SNE, and UMAP with DBSCAN.<n>The framework is demonstrated through a case study on power grid signal data, where it identifies multi-label grid event signatures, including faults and anomalies with diverse root causes.
  arXiv  Detail & Related papers  (2024-12-20T17:41:11Z)
• Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment [59.75420353684495]
  Machine learning applications on signals such as computer vision or biomedical data often face challenges due to the variability that exists across hardware devices or session recordings. In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities. We show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings.
  arXiv  Detail & Related papers  (2024-07-19T13:33:38Z)
• Deep Equilibrium Assisted Block Sparse Coding of Inter-dependent Signals: Application to Hyperspectral Imaging [71.57324258813675]
  A dataset of inter-dependent signals is defined as a matrix whose columns demonstrate strong dependencies. A neural network is employed to act as structure prior and reveal the underlying signal interdependencies. Deep unrolling and Deep equilibrium based algorithms are developed, forming highly interpretable and concise deep-learning-based architectures.
  arXiv  Detail & Related papers  (2022-03-29T21:00:39Z)
• Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization [76.68866368409216]
  We propose learning to dynamically select discretization tightness conditioned on inputs. We show that dynamically varying tightness in communication bottlenecks can improve model performance on visual reasoning and reinforcement learning tasks.
  arXiv  Detail & Related papers  (2022-02-02T23:54:26Z)
• TELESTO: A Graph Neural Network Model for Anomaly Classification in Cloud Services [77.454688257702]
  Machine learning (ML) and artificial intelligence (AI) are applied on IT system operation and maintenance. One direction aims at the recognition of re-occurring anomaly types to enable remediation automation. We propose a method that is invariant to dimensionality changes of given data.
  arXiv  Detail & Related papers  (2021-02-25T14:24:49Z)
• Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
  We propose a deep co-attention network for multi-view subspace learning. It aims to extract both the common information and the complementary information in an adversarial setting. In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
  arXiv  Detail & Related papers  (2021-02-15T18:46:44Z)
• 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)

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.