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.
arXiv:2608. 07385v1 Announce Type: cross Abstract: Learning disentangled representations is a key requirement for developing versatile, general-purpose, and sustainable models in multi-modal wearable computing.
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.
arXiv:2606. 09725v1 Announce Type: new Abstract: Disentanglement, the separation of factors of variation in data using neural networks, remains a long-standing challenge in machine learning.
arXiv:2511. 13899v2 Announce Type: replace-cross Abstract: Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity.
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.
arXiv:2408. 15344v2 Announce Type: replace Abstract: Many scientific and engineering problems involve observing a common phenomenon through multiple heterogeneous sensors or measurement modalities.
arXiv:2606. 10530v1 Announce Type: cross Abstract: Recent developments in brain recording are driving a demand for machine learning tools capable of decoding the latent structure of large populations of neurons.
Spectral-temporal unmixing of MODIS time series is essential for applications such as abundance mapping and spectral library construction, yet it remains challenging due to (i) spectral-temporal infor...
The paper investigates how variational autoencoders (VAEs) can be made more learnable in latent diffusion by analyzing diffusability through spectral properties. It introduces the Spectrum Matching Hypothesis, which posits that latents with better diffusability should have a flattened power‑law power spectral density (Encoding Spectrum Matching) and preserve frequency‑to‑frequency semantic correspondence via the decoder (Decoding Spectrum Matching). The authors implement these ideas by matching PSDs between images and latents and applying shared spectral masking, demonstrating improved diffusion generation on CelebA and ImageNet and extending the approach to representation alignment with a DoG‑based method.
The paper introduces Supervised Deep Multimodal Matrix Factorization (SD3MF), an interpretable framework that extends Symmetric Nonnegative Matrix Tri-Factorization to supervised prediction across populations of multimodal brain graphs. SD3MF learns deep hierarchical factorizations for each modality and a shared latent representation, jointly optimizing graph reconstruction and prediction while enabling data-driven multimodal fusion. Experiments on multimodal connectome datasets demonstrate that SD3MF outperforms strong deep learning baselines such as CNNs and GNNs, providing biologically interpretable insights through community-level interaction matrices.
arXiv:2610.07196v1 Announce Type: cross Abstract: Variational autoencoders are powerful representation learning models that map complex data into low-dimensional latent spaces, enabling the discovery...
arXiv:2606. 28854v1 Announce Type: cross Abstract: The common factor analytic model is related to Helmholtz and Boltzmann machines, can be conceived as a linear autoencoder, or can be thought of as a single-hidden-layer generative neural network.