Streaming weak submodularity: Interpreting neural networks on the fly

Ethan R. Elenberg, Alexandros G. Dimakis, Moran Feldman, Amin Karbasi

نتاج البحث: نشر في مجلةمقالة من مؤنمرمراجعة النظراء

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 الأصليةالإنجليزيّة
الصفحات (من إلى)4045-4055
عدد الصفحات11
دوريةAdvances in Neural Information Processing Systems
مستوى الصوت2017-December
حالة النشرنُشِر - 2017
الحدث31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, الولايات المتّحدة
المدة: ٤ ديسمبر ٢٠١٧٩ ديسمبر ٢٠١٧

ملاحظة ببليوغرافية

Publisher Copyright:
© 2017 Neural information processing systems foundation. All rights reserved.

بصمة

أدرس بدقة موضوعات البحث “Streaming weak submodularity: Interpreting neural networks on the fly'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا