ملخص
In many machine learning applications, it is important to explain the predictions of a black-box classifier. For example, why does a deep neural network assign an image to a particular class? We cast interpretability of black-box classifiers as a combinatorial maximization problem and propose an efficient streaming algorithm to solve it subject to cardinality constraints. By extending ideas from Badanidiyuru et al. [2014], we provide a constant factor approximation guarantee for our algorithm in the case of random stream order and a weakly submodular objective function. This is the first such theoretical guarantee for this general class of functions, and we also show that no such algorithm exists for a worst case stream order. Our algorithm obtains similar explanations of Inception V3 predictions 10 times faster than the state-of-the-art LIME framework of Ribeiro et al. [2016].
اللغة الأصلية | الإنجليزيّة |
---|---|
الصفحات (من إلى) | 4045-4055 |
عدد الصفحات | 11 |
دورية | Advances in Neural Information Processing Systems |
مستوى الصوت | 2017-December |
حالة النشر | نُشِر - 2017 |
الحدث | 31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, الولايات المتّحدة المدة: ٤ ديسمبر ٢٠١٧ → ٩ ديسمبر ٢٠١٧ |
ملاحظة ببليوغرافية
Publisher Copyright:© 2017 Neural information processing systems foundation. All rights reserved.