Toward Causal Representation Learning

Citations Over TimeTop 1% of 2021 papers

Abstract

The two fields of machine learning and graphical causality arose and are developed separately. However, there is, now, cross-pollination and increasing interest in both fields to benefit from the advances of the other. In this article, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, that is, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.

Related Papers

• → Personality correlates and utilitarian judgments in the everyday context: Psychopathic traits and differential effects of empathy, social dominance orientation, and dehumanization beliefs(2019)19 cited
• → Amount of altruistic punishment accounts for subsequent emotional gratification in participants with primary psychopathy(2011)14 cited
• Susquehanna Chorale Spring Concert "Roots and Wings"(2017)
• → ИСПОЛЬЗОВAНИЕ ПОТЕНЦИAЛA СОЦИAЛЬНЫХ ПAРТНЕРОВ В ПОДГОТОВКЕ БУДУЩИХ ПЕДAГОГОВ(2024)
• → The Relationship between Personality Advantage and Happiness among College Students: The Moderating Effect of Stressful Life Events(2024)