Transcription of Explainability Methods for Graph Convolutional Neural …
{{id}} {{{paragraph}}}
Example: confidence
Explainability Methods for Graph Convolutional Neural …
Explainability Methods for Graph Convolutional Neural NetworksPhillip E. Pope*HRL Laboratories, Kolouri*HRL Laboratories, RostamiHRL Laboratories, E. MartinHRL Laboratories, HoffmannHRL Laboratories, the growing use of Graph Convolutional Neural net-works (GCNNs) comes the need for Explainability . In thispaper, we introduce Explainability Methods for GCNNs. Wedevelop the Graph analogues of three prominent explain-ability Methods for Convolutional Neural networks: con-trastive gradient-based (CG) saliency maps, Class Activa-tion Mapping (CAM), and Excitation Backpropagation (EB)and their variants, gradient-weighted CAM (Grad-CAM)and contrastive EB (c-EB). We show a proof-of-concept ofthese Methods on classification problems in two applicationdomains: visual scene graphs and molecular graphs. Tocompare the Methods , we identify three desirable propertiesof explanations: (1) their importance to classification, asmeasured by the impact of occlusions, (2) their contrastiv-ity with respect to different classes, and (3) their sparsenesson a Graph .
Phillip E. Pope* HRL Laboratories, LLC pepope@hrl.com Soheil Kolouri* HRL Laboratories, LLC skolouri@hrl.com Mohammad Rostami HRL Laboratories, LLC mrostami@hrl.com Charles E. Martin HRL Laboratories, LLC cemartin@hrl.com Heiko Hoffmann HRL Laboratories, LLC hhoffmann@hrl.com Abstract With the growing use of graph convolutional neural net-
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: