Debiased Graph Neural Networks with Agnostic Label Selection Bias

01/19/2022
by   Shaohua Fan, et al.
0

Most existing Graph Neural Networks (GNNs) are proposed without considering the selection bias in data, i.e., the inconsistent distribution between the training set with test set. In reality, the test data is not even available during the training process, making selection bias agnostic. Training GNNs with biased selected nodes leads to significant parameter estimation bias and greatly impacts the generalization ability on test nodes. In this paper, we first present an experimental investigation, which clearly shows that the selection bias drastically hinders the generalization ability of GNNs, and theoretically prove that the selection bias will cause the biased estimation on GNN parameters. Then to remove the bias in GNN estimation, we propose a novel Debiased Graph Neural Networks (DGNN) with a differentiated decorrelation regularizer. The differentiated decorrelation regularizer estimates a sample weight for each labeled node such that the spurious correlation of learned embeddings could be eliminated. We analyze the regularizer in causal view and it motivates us to differentiate the weights of the variables based on their contribution on the confounding bias. Then, these sample weights are used for reweighting GNNs to eliminate the estimation bias, thus help to improve the stability of prediction on unknown test nodes. Comprehensive experiments are conducted on several challenging graph datasets with two kinds of label selection biases. The results well verify that our proposed model outperforms the state-of-the-art methods and DGNN is a flexible framework to enhance existing GNNs.

READ FULL TEXT

page 1

page 12

research
06/29/2021

Subgroup Generalization and Fairness of Graph Neural Networks

Despite enormous successful applications of graph neural networks (GNNs)...
research
09/28/2022

Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by...
research
11/25/2022

Interpreting Unfairness in Graph Neural Networks via Training Node Attribution

Graph Neural Networks (GNNs) have emerged as the leading paradigm for so...
research
11/19/2020

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks

Collider bias is a harmful form of sample selection bias that neural net...
research
11/20/2021

Generalizing Graph Neural Networks on Out-Of-Distribution Graphs

Graph Neural Networks (GNNs) are proposed without considering the agnost...
research
10/08/2021

Stable Prediction on Graphs with Agnostic Distribution Shift

Graph is a flexible and effective tool to represent complex structures i...
research
08/18/2023

Disparity, Inequality, and Accuracy Tradeoffs in Graph Neural Networks for Node Classification

Graph neural networks (GNNs) are increasingly used in critical human app...

Please sign up or login with your details

Forgot password? Click here to reset