Interpreting and Understanding Graph Convolutional Neural Network using Gradient-based Attribution Methods

by   Shangsheng Xie, et al.

In order to solve the problem that convolutional neural networks (CNN) are difficult to process non-image type relational data, Kipf et al. proposed a graph convolutional neural network (GCN). The core idea is to perform two-fold information fusion for each node in a given graph during each iteration: the fusion of graph structure information and the fusion of node feature dimensions. Although GCN has been widely used in the fields of scene semantic relationship analysis, natural language processing, and few-shot learning because of its ability to combine generalization, owing to its two-information fusion involves mathematical irreversible calculations, it is hard for GCN to explain that the predicting reason for each node classification (i.e. attribution analysis). However, the existing attribution analysis methods cannot be directly applied to the GCN because compared with the independence among CNN input data, there is correlation between GCN input data. This leads to the existing attribution method only to obtain the partial contribution of the final decision of the GCN from target node feature, the complete contribution and the contribution from neighbor nodes features cannot be obtained. To this end, we propose a gradient attribution analysis method for GCN, NAM (Node Attribution Method), can get the contribution of the target node and its neighbor nodes to the GCN output. We also propose the NIV (Node Importance Visualization) method to visualize the target node of the GCN and its neighbor nodes based on the value of the contribution value. We use the perturbation analysis method to verify the effect of NAM based on the citation network dataset. The experimental results show that NAM can well learn the contribution of each node to the node classification prediction.


Neighbor Enhanced Graph Convolutional Networks for Node Classification and Recommendation

The recently proposed Graph Convolutional Networks (GCNs) have achieved ...

Unifying Graph Convolutional Neural Networks and Label Propagation

Label Propagation (LPA) and Graph Convolutional Neural Networks (GCN) ar...

VS-CAM: Vertex Semantic Class Activation Mapping to Interpret Vision Graph Neural Network

Graph convolutional neural network (GCN) has drawn increasing attention ...

Anonymized GCN: A Novel Robust Graph Embedding Method via Hiding Node Position in Noise

Graph convolution network (GCN) have achieved state-of-the-art performan...

Graph Highway Networks

Graph Convolution Networks (GCN) are widely used in learning graph repre...

Image Retrieval for Structure-from-Motion via Graph Convolutional Network

Conventional image retrieval techniques for Structure-from-Motion (SfM) ...

3D PETCT Tumor Lesion Segmentation via GCN Refinement

Whole-body PET/CT scan is an important tool for diagnosing various malig...

Please sign up or login with your details

Forgot password? Click here to reset