Learnt Sparsification for Interpretable Graph Neural Networks

06/23/2021
by   Mandeep Rathee, et al.
8

Graph neural networks (GNNs) have achieved great success on various tasks and fields that require relational modeling. GNNs aggregate node features using the graph structure as inductive biases resulting in flexible and powerful models. However, GNNs remain hard to interpret as the interplay between node features and graph structure is only implicitly learned. In this paper, we propose a novel method called Kedge for explicitly sparsifying the underlying graph by removing unnecessary neighbors. Our key idea is based on a tractable method for sparsification using the Hard Kumaraswamy distribution that can be used in conjugation with any GNN model. Kedge learns edge masks in a modular fashion trained with any GNN allowing for gradient based optimization in an end-to-end fashion. We demonstrate through extensive experiments that our model Kedge can prune a large proportion of the edges with only a minor effect on the test accuracy. Specifically, in the PubMed dataset, Kedge learns to drop more than 80 structure has only a small contribution in comparison to node features. Finally, we also show that Kedge effectively counters the over-smoothing phenomena in deep GNNs by maintaining good task performance with increasing GNN layers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/12/2022

GPN: A Joint Structural Learning Framework for Graph Neural Networks

Graph neural networks (GNNs) have been applied into a variety of graph t...
research
05/23/2022

Learning heterophilious edge to drop: A general framework for boosting graph neural networks

Graph Neural Networks (GNNs) aim at integrating node contents with graph...
research
09/28/2020

Graph Neural Networks with Heterophily

Graph Neural Networks (GNNs) have proven to be useful for many different...
research
06/30/2020

Graph Neural Networks Including Sparse Interpretability

Graph Neural Networks (GNNs) are versatile, powerful machine learning me...
research
10/01/2020

Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking

Graph neural networks (GNNs) have become a popular approach to integrati...
research
09/09/2019

Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases

Endowing robots with human-like physical reasoning abilities remains cha...
research
11/13/2020

Learning to Drop: Robust Graph Neural Network via Topological Denoising

Graph Neural Networks (GNNs) have shown to be powerful tools for graph a...

Please sign up or login with your details

Forgot password? Click here to reset