Riemann Sum Optimization for Accurate Integrated Gradients Computation

TL;DR

RiemannOpt is a versatile framework that optimizes sample point selection in Riemann Sum approximations, significantly improving integrated gradients accuracy and reducing computational costs in neural network attribution tasks.

Contribution

It introduces RiemannOpt, a novel method for minimizing Riemann Sum errors in integrated gradients, applicable to various IG derivatives, enhancing accuracy and efficiency.

Findings

Up to 20% improvement in Insertion Scores

Reduces computational costs by up to four times

Applicable to IG, Blur IG, and Guided IG

Abstract

Integrated Gradients (IG) is a widely used algorithm for attributing the outputs of a deep neural network to its input features. Due to the absence of closed-form integrals for deep learning models, inaccurate Riemann Sum approximations are used to calculate IG. This often introduces undesirable errors in the form of high levels of noise, leading to false insights in the model's decision-making process. We introduce a framework, RiemannOpt, that minimizes these errors by optimizing the sample point selection for the Riemann Sum. Our algorithm is highly versatile and applicable to IG as well as its derivatives like Blur IG and Guided IG. RiemannOpt achieves up to 20% improvement in Insertion Scores. Additionally, it enables its users to curtail computational costs by up to four folds, thereby making it highly functional for constrained environments.