On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigms

TL;DR

This paper evaluates the assurance of fully differentiable neurosymbolic AI systems, highlighting their potential for robustness, interpretability, and data efficiency, especially in high-dimensional and class-imbalanced tasks.

Contribution

It provides the first comprehensive empirical assessment of end-to-end differentiable neurosymbolic systems' assurance across multiple domains and metrics.

Findings

Neurosymbolic models show higher assurance with arithmetic and high-dimensional inputs.

Interpretability helps identify shortcuts leading to adversarial vulnerabilities.

Data efficiency benefits are mainly in class-imbalanced reasoning tasks.

Abstract

To create usable and deployable Artificial Intelligence (AI) systems, there requires a level of assurance in performance under many different conditions. Many times, deployed machine learning systems will require more classic logic and reasoning performed through neurosymbolic programs jointly with artificial neural network sensing. While many prior works have examined the assurance of a single component of the system solely with either the neural network alone or entire enterprise systems, very few works have examined the assurance of integrated neurosymbolic systems. Within this work, we assess the assurance of end-to-end fully differentiable neurosymbolic systems that are an emerging method to create data-efficient and more interpretable models. We perform this investigation using Scallop, an end-to-end neurosymbolic library, across classification and reasoning tasks in both the image and audio domains. We assess assurance across adversarial robustness, calibration, user performance parity, and interpretability of solutions for catching misaligned solutions. We find end-to-end neurosymbolic methods present unique opportunities for assurance beyond their data efficiency through our empirical results but not across the board. We find that this class of neurosymbolic models has higher assurance in cases where arithmetic operations are defined and where there is high dimensionality to the input space, where fully neural counterparts struggle to learn robust reasoning operations. We identify the relationship between neurosymbolic models' interpretability to catch shortcuts that later result in increased adversarial vulnerability despite performance parity. Finally, we find that the promise of data efficiency is typically only in the case of class imbalanced reasoning problems.