Timezone: »

 
[S4] A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
Vadim Borisov · Johannes Meier · Johan Van den Heuvel · Hamed Jalali · Gjergji Kasneci

Tue Dec 14 09:00 AM -- 09:03 AM (PST) @
in eXplainable AI approaches for debugging and diagnosis »
Event URL: https://openreview.net/forum?id=PdxAY-yisK5 »

Understanding the results of deep neural networks is an essential step towards wider acceptance of deep learning algorithms. Many approaches address the issue of interpreting artificial neural networks, but often provide divergent explanations. Moreover, different hyperparameters of an explanatory method can lead to conflicting interpretations. In this paper, we propose a technique for aggregating the feature attributions of different explanatory algorithms using a Restricted Boltzmann machine (RBM) to achieve a more accurate and robust interpretation of deep neural networks. Several challenging experiments on real-world datasets show that the proposed RBM method outperforms popular feature attribution methods and basic ensemble techniques.

Author Information

Vadim Borisov (The University of Tuebingen)
Johannes Meier (University of Tuebingen)
Johan Van den Heuvel (University of Tuebingen)
Hamed Jalali (University of Tuebingen)
Gjergji Kasneci (University of Tuebingen)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors