GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction
Year: 2020
Type: conference-paper
Abstract: Despite the recent development in the topic of explainable AI/ML for image and text data, the majority of current solutions are not suitable to explain the prediction of neural network models when the datasets are tabular and their features are in high-dimensional vectorized formats. To mitigate this limitation, therefore, we borrow two notable ideas (i.e., "explanation by intervention" from causality and "explanation are contrastive" from philosophy) and propose a novel solution, named as GRACE, that better explains neural network models' predictions for tabular datasets. In particular, given a model's prediction as label X, GRACE intervenes and generates a minimally-modified contrastive sample to be classified as Y, with an intuitive textual explanation, answering the question of "Why X rather than Y?" We carry out comprehensive experiments using eleven public datasets of different scales and domains (e.g., # of features ranges from 5 to 216) and compare GRACE with competing baselines on different measures: fidelity, conciseness, info-gain, and influence. The user-studies show that our generated explanation is not only more intuitive and easy-to-understand but also facilitates end-users to make as much as 60% more accurate post-explanation decisions than that of Lime.
Authors: Thai Le, Suhang Wang, Dongwon Lee
Institution: Pennsylvania State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funder: National Science Foundation
Awards: Developing and Evaluating Fraud Informatics Curriculum among Institutions in the Appalachian Region, Vertical Search Engine and Graph Homomorphism for Enhancing the Cybersecurity Workforce, EAGER: Training Computers and Humans to Detect Misinformation by Combining Computational and Theoretical Analysis, EAGER: SaTC: Early-Stage Interdisciplinary Collaboration: Modeling Memory Illusion for Predicting Trust in Online Information, III: Small: Collaborative Research: Effective Labeled Data Generation via Generative Adversarial Learning
OpenAlex ID: W3081364375
