English

Learning Discrete Concepts in Latent Hierarchical Models

Machine Learning 2025-01-16 v2 Artificial Intelligence Machine Learning

Abstract

Learning concepts from natural high-dimensional data (e.g., images) holds potential in building human-aligned and interpretable machine learning models. Despite its encouraging prospect, formalization and theoretical insights into this crucial task are still lacking. In this work, we formalize concepts as discrete latent causal variables that are related via a hierarchical causal model that encodes different abstraction levels of concepts embedded in high-dimensional data (e.g., a dog breed and its eye shapes in natural images). We formulate conditions to facilitate the identification of the proposed causal model, which reveals when learning such concepts from unsupervised data is possible. Our conditions permit complex causal hierarchical structures beyond latent trees and multi-level directed acyclic graphs in prior work and can handle high-dimensional, continuous observed variables, which is well-suited for unstructured data modalities such as images. We substantiate our theoretical claims with synthetic data experiments. Further, we discuss our theory's implications for understanding the underlying mechanisms of latent diffusion models and provide corresponding empirical evidence for our theoretical insights.

Keywords

Cite

@article{arxiv.2406.00519,
  title  = {Learning Discrete Concepts in Latent Hierarchical Models},
  author = {Lingjing Kong and Guangyi Chen and Biwei Huang and Eric P. Xing and Yuejie Chi and Kun Zhang},
  journal= {arXiv preprint arXiv:2406.00519},
  year   = {2025}
}

Comments

NeurIPS 2024

R2 v1 2026-06-28T16:49:43.605Z