Loop Polarity Analysis to Avoid Underspecification in Deep Learning

TL;DR

This paper introduces loop polarity analysis to specify causal structures in deep learning, enhancing robustness and out-of-distribution performance by understanding feedback loops in system dynamics.

Contribution

It proposes using loop polarity analysis to encode causal structures, improving deep learning robustness against distribution shifts.

Findings

Measuring feedback loop polarity improves model robustness

Enhanced out-of-distribution performance demonstrated with epidemic data

Integrates system dynamics concepts into deep learning pipeline

Abstract

Deep learning is a powerful set of techniques for detecting complex patterns in data. However, when the causal structure of that process is underspecified, deep learning models can be brittle, lacking robustness to shifts in the distribution of the data-generating process. In this paper, we turn to loop polarity analysis as a tool for specifying the causal structure of a data-generating process, in order to encode a more robust understanding of the relationship between system structure and system behavior within the deep learning pipeline. We use simulated epidemic data based on an SIR model to demonstrate how measuring the polarity of the different feedback loops that compose a system can lead to more robust inferences on the part of neural networks, improving the out-of-distribution performance of a deep learning model and infusing a system-dynamics-inspired approach into the machine learning development pipeline.