Year: 2026
Type: preprint
Abstract: Probabilistic graphical models (PGMs) are widely used to discover latent structure in data, but their success hinges on selecting an appropriate model design. In practice, model specification is difficult and often requires iterative trial-and-error. This challenge arises because classical PGMs typically operate on individual datasets. In this work, we consider settings involving collections of related datasets and propose meta-probabilistic modeling (MPM) to learn the generative model structure itself. MPM uses a hierarchical formulation in which global components encode shared patterns across datasets, while local parameters capture dataset-specific latent structure. For scalable learning and inference, we derive a tractable VAE-inspired surrogate objective together with a bi-level optimization algorithm. Our methodology supports a broad class of expressive probabilistic models and has connections to existing architectures, such as Slot Attention. Experiments on object-centric representation learning and sequential text modeling demonstrate that MPM effectively adapts generative models to data while recovering meaningful latent representations.
Source: arXiv (Cornell University)
Authors: Zhang, Kevin, Wang, Yixin
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Toward Automated Uncertainty Quantification in Causal Inference, ACED: Tail-aware Generative Modeling for Inverse Discovery of Molecules, Collaborative Research: ATD: Hawkes Process-Based Causal Relationship Discovery For Complex Threat Detection and Forecasting, CAREER: Bringing Structure to the Unstructured: Robust Causal and Statistical Modeling of High-dimensional Unstructured Data, G8101864701, G8876996369
OpenAlex ID: W7119604597
Cites:
Cited by:
Related to: