Causal Deep Learning

Abstract

Causality has the potential to truly transform the way we solve a large number of realworld problems. Yet, so far, its potential remains largely unlocked since most work so far requires strict assumptions which do not hold true in practice. To address this challenge and make progress in solving real-world problems, we propose a new way of thinking about causality -we call this causal deep learning. The framework which we propose for causal deep learning spans three dimensions: (1) a structural dimension, which allows incomplete causal knowledge rather than assuming either full or no causal knowledge; (2) a parametric dimension, which encompasses parametric forms which are typically ignored; and finally, (3) a temporal dimension, which explicitly allows for situations which capture exposure times or temporal structure. Together, these dimensions allow us to make progress on a variety of real-world problems by leveraging (sometimes incomplete) causal knowledge and/or combining diverse causal deep learning methods. This new framework also enables researchers to compare systematically across existing works as well as identify promising research areas which can lead to real-world impact.

Deep learning for low-data drug discovery: hurdles and opportunities

“…Awareness of prediction uncertainty and out-ofdistribution performance are expected to become crucial guides in the future for prospective decision making, especially in low-data scenarios. We also expect causal [58] and explainable deep learning [59] to become instrumental tools in low-data scenarios and for out-ofdomain generalization, by shedding light on causal relationships, spurious correlations, and potential model shortcuts.…”