Restricting the Flow: Information Bottlenecks for Attribution

Autor:	Schulz, Karl, Sixt, Leon, Tombari, Federico, Landgraf, Tim
Rok vydání:	2020
Předmět:	Statistics - Machine Learning Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In this work we adapt the information bottleneck concept for attribution. By adding noise to intermediate feature maps we restrict the flow of information and can quantify (in bits) how much information image regions provide. We compare our method against ten baselines using three different metrics on VGG-16 and ResNet-50, and find that our methods outperform all baselines in five out of six settings. The method's information-theoretic foundation provides an absolute frame of reference for attribution values (bits) and a guarantee that regions scored close to zero are not necessary for the network's decision. For reviews: https://openreview.net/forum?id=S1xWh1rYwB For code: https://github.com/BioroboticsLab/IBA Comment: 18 pages, 12 figures, accepted at ICLR 2020 (Oral)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2001.00396 Zobrazit plný text záznamu View this record from Arxiv