Timezone: »
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%) of the negative effects introduced by biased training data. On the largest dataset we consider, ogb-arxiv, we observe an 2% absolute improvement over the baseline and reduce 30% of the negative effects.
Author Information
Qi Zhu (University of Illinois, Urbana Champaign)
Natalia Ponomareva (Google)
Jiawei Han (University of Illinois at Urbana-Champaign)
Bryan Perozzi (Google)
More from the Same Authors
-
2021 : Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance »
Shibal Ibrahim · Natalia Ponomareva · Rahul Mazumder -
2021 Poster: Universal Graph Convolutional Networks »
Di Jin · Zhizhi Yu · Cuiying Huo · Rui Wang · Xiao Wang · Dongxiao He · Jiawei Han -
2021 Poster: Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization »
Qi Zhu · Carl Yang · Yidan Xu · Haonan Wang · Chao Zhang · Jiawei Han -
2021 Poster: COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining »
Yu Meng · Chenyan Xiong · Payal Bajaj · saurabh tiwary · Paul Bennett · Jiawei Han · XIA SONG -
2014 Poster: Robust Tensor Decomposition with Gross Corruption »
Quanquan Gu · Huan Gui · Jiawei Han -
2012 Poster: Selective Labeling via Error Bound Minimization »
Quanquan Gu · Tong Zhang · Chris Ding · Jiawei Han -
2009 Poster: Graph-based Consensus Maximization among Multiple Supervised and Unsupervised Models »
Jing Gao · Feng Liang · Wei Fan · Yizhou Sun · Jiawei Han