DeepAI AI Chat
Log In Sign Up

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

by   Maximilian Stadler, et al.

The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNN). Nonetheless, uncertainty estimation for non-independent node-level predictions is under-explored. In this work, we explore uncertainty quantification for node classification in three ways: (1) We derive three axioms explicitly characterizing the expected predictive uncertainty behavior in homophilic attributed graphs. (2) We propose a new model Graph Posterior Network (GPN) which explicitly performs Bayesian posterior updates for predictions on interdependent nodes. GPN provably obeys the proposed axioms. (3) We extensively evaluate GPN and a strong set of baselines on semi-supervised node classification including detection of anomalous features, and detection of left-out classes. GPN outperforms existing approaches for uncertainty estimation in the experiments.


page 41

page 42


Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation

Graph Neural Networks (GNNs) have been predominant for graph learning ta...

Uncertainty Aware Semi-Supervised Learning on Graph Data

Thanks to graph neural networks (GNNs), semi-supervised node classificat...

Uncertainty Propagation in Node Classification

Quantifying predictive uncertainty of neural networks has recently attra...

PI-GNN: A Novel Perspective on Semi-Supervised Node Classification against Noisy Labels

Semi-supervised node classification, as a fundamental problem in graph l...

A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs

Current graph neural networks (GNNs) that tackle node classification on ...

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

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

Energy-based Out-of-Distribution Detection for Graph Neural Networks

Learning on graphs, where instance nodes are inter-connected, has become...