AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark

TL;DR

AGOP-IxG is a fast, accurate local feature attribution method for tabular data that outperforms several baselines in synthetic tests and offers significant speed advantages, with evaluations on real datasets.

Contribution

The paper introduces AGOP-IxG, a novel gradient covariance filter for local feature attribution, and provides a controlled benchmark for evaluating attribution methods on tabular data.

Findings

AGOP-IxG outperforms baselines on synthetic datasets in correlation and noise detection.

It is approximately 350 to 1650 times faster than SHAP.

On real datasets, it shows comparable global faithfulness to other methods.

Abstract

Automated machine learning pipelines increasingly produce models whose predictions must be explained to end users, auditors, and downstream decision systems. The most widely used feature attribution methods (SHAP, Integrated Gradients, LIME) are typically chosen by convention rather than measured fidelity, because rigorous evaluation is impeded by the absence of ground-truth attribution on real data. We propose AGOP-IxG, a fast per-sample attribution method for tabular classifiers that pre-multiplies the per-sample gradient by a top-$K$ rank-truncated Average Gradient Outer Product matrix, and evaluate it against four widely-used baselines on a controlled tabular benchmark designed for AutoML practitioners. In Part 1, we construct three synthetic multi-class tabular tasks (linear, sparse nonlinear, interaction-based) where ground-truth attribution per sample is analytically or numerically derivable, and compare five methods: AGOP-IxG, SHAP (DeepExplainer), Integrated Gradients, InputXGradient, and LIME. AGOP-IxG leads on Spearman rank correlation and noise feature mass on all three synthetic datasets, and on top-$k$ precision on the interaction dataset. Across all settings, AGOP-IxG is approximately $350\times$ to $1{,}650\times$ faster than SHAP. In Part 2, we evaluate global faithfulness on Adult Income and Credit Card Default using the ROAR protocol; the methods cluster within $\sim 1.7\%$ relative AUC, consistent with AGOP-IxG being optimized for per-sample local attribution rather than global feature ranking.