Robust Attribution Regularization
An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatically attributing a neural network's output change to its input change. We propose training objectives in classic robust optimization models to achieve robust IG attributions. Our objectives give principled generalizations of previous objectives designed for robust predictions, and they naturally degenerate to classic soft-margin training for one-layer neural networks. We also generalize previous theory and prove that the objectives for different robust optimization models are closely related. Experiments demonstrate the effectiveness of our method, and also point to intriguing problems which hint at the need for better optimization techniques or better neural network architectures for robust attribution training.
Code (1)
Similar Papers 제목 키워드 기반
Individualized and Global Feature Attributions for Gradient Boosted Trees in the Presence of $\ell_2$ Regularization
While $\ell_2$ regularization is widely used in training gradient boosted trees, popular individualized feature attribution methods for trees such as Saabas and TreeSHAP overlook the training procedure. We propose Predic…
Additive modelsfeature selectionImproving Adversarial Robustness of Attribution via Implicit Regularization
The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this w…
Adversarial RobustnessSHAP-Guided Regularization in Machine Learning Models
Feature attribution methods such as SHapley Additive exPlanations (SHAP) have become instrumental in understanding machine learning models, but their role in guiding model optimization remains underexplored. In this pape…
Feature ImportanceTANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
Despite their success with unstructured data, deep neural networks are not yet a panacea for structured tabular data. In the tabular domain, their efficiency crucially relies on various forms of regularization to prevent…
Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI. Despite a recent surge o…
Sensitivity