Data-adaptive discriminative feature localization with statistically guaranteed interpretation

DOI10.1214/22-AOAS1705MaRDI QIDQ6179110zbMATH OpenOpenAlexFDO

Authors Ben Dai, Xiaotong Shen, Lin Yee Chen, Chunlin Li, Wei Pan

Publication date 16 January 2024

Published in The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2211.10061

zbMATH Keywords

deep learningdiscriminative featuresexplainable artificial intelligencegeneralized partial \(R^2\)interpretabilitylocalizationregularization

Mathematics Subject Classification ID

Applications of statistics (62Pxx)

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.

Cites work

• 10.1162/153244303321897690
• A note on a general definition of the coefficient of determination
• A note on margin-based loss functions in classification
• Convexity, Classification, and Risk Bounds
• Early stopping and non-parametric regression: an optimal data-dependent stopping rule
• Greedy function approximation: A gradient boosting machine.
• scientific article; zbMATH DE number 6276119 (Why is no real title available?)
• Local Rademacher complexities
• Random forests
• Robust Truncated Hinge Loss Support Vector Machines
• Support-vector networks

This page was built for publication: Data-adaptive discriminative feature localization with statistically guaranteed interpretation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6179110)