Explaining a black-box using Deep Variational Information Bottleneck Approach

2019/02/19 by Bang, Seojin, Xie, Pengtao, Lee, Heewook +2 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1902.06918

Abstract

Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, information bottleneck principle, as a criterion for finding such explanations. For each instance, VIBI selects key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box system on that input (comprehensive). We evaluate VIBI on three datasets and compare with state-of-the-art interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics

Cited by

• Training deep physical neural networks with local physical information bottleneck

Related

• The Information Bottleneck Problem and Its Applications in Machine\n Learning
• Shedding Light on Black Box Machine Learning Algorithms: Development of an Axiomatic Framework to Assess the Quality of Methods that Explain Individual Predictions
• Open the Black Box Data-Driven Explanation of Black Box Decision Systems
• What made you do this? Understanding black-box decisions with sufficient\n input subsets
• Information Bottleneck and its Applications in Deep Learning