DIVIDE: A Framework for Learning from Independent Multi-Mechanism Data Using Deep Encoders and Gaussian Processes
This work addresses the challenge of interpreting complex scientific data with multiple generative factors, such as in materials science, by providing a method for mechanism-aware prediction and active learning, though it is incremental as it builds on existing deep learning and Gaussian Process techniques.
The authors tackled the problem of disentangling multiple independent mechanisms in scientific datasets by introducing DIVIDE, a framework that integrates mechanism-specific deep encoders with a structured Gaussian Process, achieving robust separation and reproduction of additive and scaled interactions across synthetic and experimental benchmarks.
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.