Layerwise Relevance Visualization in Convolutional Text Graph Classifiers

Robert Schwarzenberg, Marc Hübner, David Harbecke, Christoph Alt, Leonhard Hennig


Abstract
Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain. Graph Convolutional Networks (GCN) allow this projection, but existing explainability methods do not exploit this fact, i.e. do not focus their explanations on intermediate states. In this work, we present a novel method that traces and visualizes features that contribute to a classification decision in the visible and hidden layers of a GCN. Our method exposes hidden cross-layer dynamics in the input graph structure. We experimentally demonstrate that it yields meaningful layerwise explanations for a GCN sentence classifier.
Anthology ID:
D19-5308
Volume:
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)
Month:
November
Year:
2019
Address:
Hong Kong
Editors:
Dmitry Ustalov, Swapna Somasundaran, Peter Jansen, Goran Glavaš, Martin Riedl, Mihai Surdeanu, Michalis Vazirgiannis
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–62
Language:
URL:
https://aclanthology.org/D19-5308
DOI:
10.18653/v1/D19-5308
Bibkey:
Cite (ACL):
Robert Schwarzenberg, Marc Hübner, David Harbecke, Christoph Alt, and Leonhard Hennig. 2019. Layerwise Relevance Visualization in Convolutional Text Graph Classifiers. In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), pages 58–62, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers (Schwarzenberg et al., TextGraphs 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5308.pdf
Attachment:
 D19-5308.Attachment.pdf
Code
 DFKI-NLP/lrv