Journal
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022
Volume -, Issue -, Pages 4640-4644Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3511808.3557556
Keywords
Graph Neural Networks; Uncertainty Estimation; Hypernetworks
Categories
Ask authors/readers for more resources
This research investigates automated graph neural network calibration by incorporating uncertainty estimation into hyperparameter optimization problem, proposing a hyperparameter uncertainty-induced graph convolutional network with promising results. Experimental results demonstrate the effectiveness of the proposed method in terms of node classification accuracy and expected calibration error compared to several state-of-the-art uncertainty-aware and calibrated GCN methods.
Automated graph learning has drawn widespread research attention due to its great potential to reduce human efforts when dealing with graph data, among which hyperparameter optimization (HPO) is one of the mainstream directions and has made promising progress. However, how to obtain reliable and trustworthy prediction results with automated graph neural networks (GNN) is still quite underexplored. To this end, we investigate automated GNN calibration by marrying uncertainty estimation to the HPO problem. Specifically, we propose a hyperparameter uncertainty-induced graph convolutional network (HyperU-GCN) with a bilevel formulation, where the upper-level problem explicitly reasons uncertainties by developing a probabilistic hypernetworks through a variational Bayesian lens, while the lower-level problem learns how the GCN weights respond to a hyperparameter distribution. By squeezing model uncertainty into the hyperparameter space, the proposed HyperU-GCN could achieve calibrated predictions in a similar way to Bayesian model averaging over hyperparameters. Extensive experimental results on six public datasets were provided in terms of node classification accuracy and expected calibration error (ECE), demonstrating the effectiveness of our approach compared with several state-of-the-art uncertainty-aware and calibrated GCN methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available