
Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations
With the development of graph convolutional networks (GCN), deep learnin...
read it

A Simple Spectral Failure Mode for Graph Convolutional Networks
We present a simple generative model in which spectral graph embedding f...
read it

Graph convolutional networks for learning with few clean and many noisy labels
In this work we consider the problem of learning a classifier from noisy...
read it

Distributed Graph Convolutional Networks
The aim of this work is to develop a fullydistributed algorithmic frame...
read it

L^2GCN: LayerWise and Learned Efficient Training of Graph Convolutional Networks
Graph convolution networks (GCN) are increasingly popular in many applic...
read it

Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks
The performance limit of Graph Convolutional Networks (GCNs) and the fac...
read it

Latent Patient Network Learning for Automatic Diagnosis
Recently, Graph Convolutional Networks (GCNs) has proven to be a powerfu...
read it
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers
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 crosslayer dynamics in the input graph structure. We experimentally demonstrate that it yields meaningful layerwise explanations for a GCN sentence classifier.
READ FULL TEXT
Comments
There are no comments yet.