Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation

Abstract

In explainable artificial intelligence, discriminative feature localization is critical to reveal a blackbox model's decision-making process from raw data to prediction. In this article, we use two real datasets, the MNIST handwritten digits and MIT-BIH Electrocardiogram (ECG) signals, to motivate key characteristics of discriminative features, namely adaptiveness, predictive importance and effectiveness. Then, we develop a localization framework based on adversarial attacks to effectively localize discriminative features. In contrast to existing heuristic methods, we also provide a statistically guaranteed interpretability of the localized features by measuring a generalized partial $R^2$. We apply the proposed method to the MNIST dataset and the MIT-BIH dataset with a convolutional auto-encoder. In the first, the compact image regions localized by the proposed method are visually appealing. Similarly, in the second, the identified ECG features are biologically plausible and consistent with cardiac electrophysiological principles while locating subtle anomalies in a QRS complex that may not be discernible by the naked eye. Overall, the proposed method compares favorably with state-of-the-art competitors. Accompanying this paper is a Python library dnn-locate (https://dnn-locate.readthedocs.io/en/latest/) that implements the proposed approach.

arXiv comment27 pages, 11 figures

References in corpus (13)

• A Unified Approach to Interpreting Model Predictions
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
• ECG Heartbeat Classification: A Deep Transferable Representation
• Local Rademacher complexities
• Learning how to explain neural networks: PatternNet and PatternAttribution
• Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition
• Early stopping and non-parametric regression: An optimal data-dependent stopping rule
• Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
• Significance tests of feature relevance for a black-box learner
• Generalization error for multi-class margin classification
• Generalization Bounds for Convolutional Neural Networks