Loop Polarity Analysis to Avoid Underspecification in Deep Learning
This addresses robustness issues in deep learning for applications like epidemic modeling, but it is incremental as it applies an existing system-dynamics method to a new context.
The paper tackles the problem of deep learning models being brittle due to underspecified causal structures in data-generating processes, using loop polarity analysis to encode robust system understanding, resulting in improved out-of-distribution performance on simulated epidemic data.
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.