DIVIDE: A Framework for Learning from Independent Multi-Mechanism Data Using Deep Encoders and Gaussian Processes

• URL: http://arxiv.org/abs/2511.12745v1
• Date: Sun, 16 Nov 2025 19:22:59 GMT
• Title: DIVIDE: A Framework for Learning from Independent Multi-Mechanism Data Using Deep Encoders and Gaussian Processes
• Authors: Vivek Chawla, Boris Slautin, Utkarsh Pratiush, Dayakar Penumadu, Sergei Kalinin,
• Abstract summary: DIVIDE is a framework that disentangles independent generative factors from their combined effect with uncertainty.<n>It is demonstrated on synthetic datasets combining categorical image patches with nonlinear spatial fields.<n>The framework extends naturally to multifunctional datasets where mechanical, electromagnetic or optical responses coexist.
• Score: 0.656854444547614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific datasets often arise from multiple independent mechanisms such as spatial, categorical or structural effects, whose combined influence obscures their individual contributions. We introduce DIVIDE, a framework that disentangles these influences by integrating mechanism-specific deep encoders with a structured Gaussian Process in a joint latent space. Disentanglement here refers to separating independently acting generative factors. The encoders isolate distinct mechanisms while the Gaussian Process captures their combined effect with calibrated uncertainty. The architecture supports structured priors, enabling interpretable and mechanism-aware prediction as well as efficient active learning. DIVIDE is demonstrated on synthetic datasets combining categorical image patches with nonlinear spatial fields, on FerroSIM spin lattice simulations of ferroelectric patterns, and on experimental PFM hysteresis loops from PbTiO3 films. Across benchmarks, DIVIDE separates mechanisms, reproduces additive and scaled interactions, and remains robust under noise. The framework extends naturally to multifunctional datasets where mechanical, electromagnetic or optical responses coexist.

Related papers

• Learning ORDER-Aware Multimodal Representations for Composite Materials Design [15.819480337529741]
  We introduce ORDinal-aware imagE-tabulaR alignment (ORDER), a multimodal pretraining framework that establishes ordinality as a core principle for composite material representations.<n>ORDER ensures that materials with similar target properties occupy nearby regions in the latent space, which effectively preserves the continuous nature of composite properties.
  arXiv  Detail & Related papers  (2026-01-23T06:39:01Z)
• Autonomous Probe Microscopy with Robust Bag-of-Features Multi-Objective Bayesian Optimization: Pareto-Front Mapping of Nanoscale Structure-Property Trade-Offs [0.837047113864403]
  Combinatorial materials libraries are an efficient route to generate large families of candidate compositions.<n>We develop an autonomous scanning probe microscopy framework that integrates automated atomic force and magnetic force microscopy.
  arXiv  Detail & Related papers  (2026-01-09T04:55:36Z)
• Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning [52.26396748560348]
  We provide an overview of high dimensional dynamical systems driven by random matrices.<n>We focus on applications to simple models of learning and generalization in machine learning theory.
  arXiv  Detail & Related papers  (2026-01-03T00:12:32Z)
• Domain Switching on the Pareto Front: Multi-Objective Deep Kernel Learning in Automated Piezoresponse Force Microscopy [2.5041807796023425]
  Ferroelectric polarization switching underpins the functional performance of a wide range of materials and devices.<n>Here, we introduce a multi-objective kernel-learning workflow that infers the microstructural rules governing switching behavior directly from imaging data.<n>While demonstrated for ferroelectric domain switching, our approach provides a powerful, generalizable tool for navigating complex, non-differentiable design spaces.
  arXiv  Detail & Related papers  (2025-06-09T17:58:27Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• Multi-branch of Attention Yields Accurate Results for Tabular Data [8.017123125747258]
  We propose MAYA, an encoder-decoder transformer-based framework.<n>In the encoder, we design a Multi-Branch of Attention (MBA) that constructs multiple parallel attention branches.<n>We employ collaborative learning with a dynamic consistency weight constraint to produce more robust representations.
  arXiv  Detail & Related papers  (2025-02-18T03:43:42Z)
• A Data-Driven Framework for Discovering Fractional Differential Equations in Complex Systems [8.206685537936078]
  This study introduces a stepwise data-driven framework for discovering fractional differential equations (FDEs) directly from data.<n>Our framework applies deep neural networks as surrogate models for denoising and reconstructing sparse and noisy observations.<n>We validate the framework across various datasets, including synthetic anomalous diffusion data and experimental data on the creep behavior of frozen soils.
  arXiv  Detail & Related papers  (2024-12-05T08:38:30Z)
• iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models [48.33685559041322]
  This paper focuses on identifying the causal mechanism shifts in two or more related datasets over the same set of variables. Code implementing the proposed method is open-source and publicly available at https://github.com/kevinsbello/iSCAN.
  arXiv  Detail & Related papers  (2023-06-30T01:48:11Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Discrete-Valued Neural Communication [85.3675647398994]
  We show that restricting the transmitted information among components to discrete representations is a beneficial bottleneck. Even though individuals have different understandings of what a "cat" is based on their specific experiences, the shared discrete token makes it possible for communication among individuals to be unimpeded by individual differences in internal representation. We extend the quantization mechanism from the Vector-Quantized Variational Autoencoder to multi-headed discretization with shared codebooks and use it for discrete-valued neural communication.
  arXiv  Detail & Related papers  (2021-07-06T03:09:25Z)
• Transformers with Competitive Ensembles of Independent Mechanisms [97.93090139318294]
  We propose a new Transformer layer which divides the hidden representation and parameters into multiple mechanisms, which only exchange information through attention. We study TIM on a large-scale BERT model, on the Image Transformer, and on speech enhancement and find evidence for semantically meaningful specialization as well as improved performance.
  arXiv  Detail & Related papers  (2021-02-27T21:48:46Z)

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.