Structural Equation-VAE: Disentangled Latent Representations for Tabular Data
This work addresses the problem of interpretable generative modeling for scientific and social domains where theory-driven constructs are essential, though it appears incremental as it builds on existing VAE and structural equation modeling approaches.
The authors tackled the challenge of learning interpretable latent representations from tabular data by introducing SE-VAE, a novel architecture that embeds structural equation modeling into a VAE to align latent subspaces with known groupings and isolate confounding variation, resulting in consistent outperformance over baselines in factor recovery, interpretability, and robustness.
Learning interpretable latent representations from tabular data remains a challenge in deep generative modeling. We introduce SE-VAE (Structural Equation-Variational Autoencoder), a novel architecture that embeds measurement structure directly into the design of a variational autoencoder. Inspired by structural equation modeling, SE-VAE aligns latent subspaces with known indicator groupings and introduces a global nuisance latent to isolate construct-specific confounding variation. This modular architecture enables disentanglement through design rather than through statistical regularizers alone. We evaluate SE-VAE on a suite of simulated tabular datasets and benchmark its performance against a series of leading baselines using standard disentanglement metrics. SE-VAE consistently outperforms alternatives in factor recovery, interpretability, and robustness to nuisance variation. Ablation results reveal that architectural structure, rather than regularization strength, is the key driver of performance. SE-VAE offers a principled framework for white-box generative modeling in scientific and social domains where latent constructs are theory-driven and measurement validity is essential.