Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

arXiv:2402.09236v1 Announce Type: new
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 …

abstract arxiv build concepts cs.ai cs.lg foundation intelligent learning systems machine machine learning math.st representation representation learning stat.ml stat.th systems type understanding