Transcription of Explainability Methods for Graph Convolutional Neural …
{{id}} {{{paragraph}}}
Example: air traffic controller
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.
of graph signal processing [3, 4] and spectral graph theory in which signal operations like Fourier transform and con-volutions are extended to signals living on graphs. GCNNs emerged from the spectral graph theory, e.g., as introduced by Bruna et al. [2] or Henaff et al. [12]. GCNNs based on spectral graph theory enable definition of ...
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: