Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data

by   Qi Zhu, et al.

There has been a recent surge of interest in designing Graph Neural Networks (GNNs) for semi-supervised learning tasks. Unfortunately this work has assumed that the nodes labeled for use in training were selected uniformly at random (i.e. are an IID sample). However in many real world scenarios gathering labels for graph nodes is both expensive and inherently biased – so this assumption can not be met. GNNs can suffer poor generalization when this occurs, by overfitting to superfluous regularities present in the training data. In this work we present a method, Shift-Robust GNN (SR-GNN), designed to account for distributional differences between biased training data and the graph's true inference distribution. SR-GNN adapts GNN models for the presence of distributional shifts between the nodes which have had labels provided for training and the rest of the dataset. We illustrate the effectiveness of SR-GNN in a variety of experiments with biased training datasets on common GNN benchmark datasets for semi-supervised learning, where we see that SR-GNN outperforms other GNN baselines by accuracy, eliminating at least ( 40 negative effects introduced by biased training data. On the largest dataset we consider, ogb-arxiv, we observe an 2 and reduce 30


page 1

page 2

page 3

page 4


Addressing the Impact of Localized Training Data in Graph Neural Networks

Graph Neural Networks (GNNs) have achieved notable success in learning f...

Graph Random Neural Network

Graph neural networks (GNNs) have generalized deep learning methods into...

Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift

The concern of overconfident mis-predictions under distributional shift ...

IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research

Graph neural networks (GNNs) have shown high potential for a variety of ...

Distributional Signals for Node Classification in Graph Neural Networks

In graph neural networks (GNNs), both node features and labels are examp...

Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing

Recent research has shown that Graph Neural Networks (GNNs) can learn po...

GNN-LM: Language Modeling based on Global Contexts via GNN

Inspired by the notion that “to copy is easier than to memorize“, in thi...

Please sign up or login with your details

Forgot password? Click here to reset