← Back to all news
arXiv Machine Learning By Ioannis N. Ziogas, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis

Variational decomposition autoencoding improves disentanglement of latent representations

Read the original on arXiv Machine Learning →

The paper introduces variational decomposition autoencoding (VDA), a framework that biases signal decomposition into latent representations. VDA is realized as variational decomposition autoencoders (DecVAEs), encoder-only networks that learn multiple latent subspaces aligned with time‑frequency characteristics. Experiments on simulated data and three speech datasets show that DecVAEs outperform traditional VAEs in disentanglement quality and robustness, producing factor‑specific latent subspaces when generative factors have distinct spectral signatures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 16

Complete or Sparse: A Tale of Two Identifiabilities

The paper investigates when supervised learning can recover the true latent variables that generate data, focusing on two causal settings: generative (labels cause latents) and discriminative (latents cause labels). It shows that if the representation space has at least as many dimensions as the latent space, optimal encoders are linear; otherwise, identifiability fails and encoders become nonlinear. Additional constraints—such as non‑negative activations in the generative case or sparsity and spark conditions in the discriminative case—enable recovery of individual latent variables, linking nonlinear ICA, compressed sensing, and neural network interpretability.

By Junze Zhou, David Klindt
llmsdiffusionbenchmarkssafetydata-engineering
More like this →
arXiv Computer Vision
Oct 28

Multi-task Disentangling Fusion Mamba-CNN for MODIS Spectral-Temporal Unmixing with Endmember Variability Modeling

The paper introduces Multi-task Disentangling Fusion Mamba (MDF-Mamba), a framework for spectral-temporal unmixing of MODIS time series. It uses a disentangling architecture that pairs per-channel spectral experts with a bidirectional Mamba temporal branch, and integrates their outputs via a manifold-constrained hyper-connection (mHCFusion). The method also models endmember variability with pixel-wise learnable weights and employs a multi-task training objective combining supervised abundance estimation, self-supervised spectral reconstruction, and endmember regularization, achieving top performance on most evaluation metrics for Alberta and Saskatchewan datasets.

By Motasem Alkayid, Yimin Zhu, Naser El-Sheimy, Lincoln Linlin Xu
More like this →