Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

09/28/2022
by   Shaohua Fan, et al.
69

Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by learning the correlation between the input graphs and labels. However, by presenting a graph classification investigation on the training graphs with severe bias, surprisingly, we discover that GNNs always tend to explore the spurious correlations to make decision, even if the causal correlation always exists. This implies that existing GNNs trained on such biased datasets will suffer from poor generalization capability. By analyzing this problem in a causal view, we find that disentangling and decorrelating the causal and bias latent variables from the biased graphs are both crucial for debiasing. Inspiring by this, we propose a general disentangled GNN framework to learn the causal substructure and bias substructure, respectively. Particularly, we design a parameterized edge mask generator to explicitly split the input graph into causal and bias subgraphs. Then two GNN modules supervised by causal/bias-aware loss functions respectively are trained to encode causal and bias subgraphs into their corresponding representations. With the disentangled representations, we synthesize the counterfactual unbiased training samples to further decorrelate causal and bias variables. Moreover, to better benchmark the severe bias problem, we construct three new graph datasets, which have controllable bias degrees and are easier to visualize and explain. Experimental results well demonstrate that our approach achieves superior generalization performance over existing baselines. Furthermore, owing to the learned edge mask, the proposed model has appealing interpretability and transferability. Code and data are available at: https://github.com/googlebaba/DisC.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/19/2022

Debiased Graph Neural Networks with Agnostic Label Selection Bias

Most existing Graph Neural Networks (GNNs) are proposed without consider...
research
11/20/2021

Generalizing Graph Neural Networks on Out-Of-Distribution Graphs

Graph Neural Networks (GNNs) are proposed without considering the agnost...
research
06/24/2022

On Structural Explanation of Bias in Graph Neural Networks

Graph Neural Networks (GNNs) have shown satisfying performance in variou...
research
01/30/2022

Discovering Invariant Rationales for Graph Neural Networks

Intrinsic interpretability of graph neural networks (GNNs) is to find a ...
research
07/03/2021

Learning Debiased Representation via Disentangled Feature Augmentation

Image classification models tend to make decisions based on peripheral a...
research
03/29/2022

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

This paper proposes a new eXplanation framework, called OrphicX, for gen...
research
07/18/2023

Rumor Detection with Diverse Counterfactual Evidence

The growth in social media has exacerbated the threat of fake news to in...

Please sign up or login with your details

Forgot password? Click here to reset