Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models
Abstract
To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causal representation learning. The other approach is to build highly-performant foundation models and then invest efforts into understanding how they work. In this work, we relate these two approaches and study how to learn human-interpretable concepts from data. Weaving together ideas from both fields, we formally define a notion of concepts and show that they can be provably recovered from diverse data. Experiments on synthetic data and large language models show the utility of our unified approach.
Cite
@article{arxiv.2402.09236,
title = {Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models},
author = {Goutham Rajendran and Simon Buchholz and Bryon Aragam and Bernhard Schölkopf and Pradeep Ravikumar},
journal= {arXiv preprint arXiv:2402.09236},
year = {2024}
}
Comments
To appear in NeurIPS 2024 under the modified title 'From Causal to Concept-Based Representation Learning'