Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

10/26/2021
by   Maximilian Stadler, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 41

page 42

10/24/2020

Uncertainty Aware Semi-Supervised Learning on Graph Data

Thanks to graph neural networks (GNNs), semi-supervised node classificat...
06/14/2021

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

Semi-supervised node classification, as a fundamental problem in graph l...
02/10/2020

Bilinear Graph Neural Network with Node Interactions

Graph Neural Network (GNN) is a powerful model to learn representations ...
12/24/2020

Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks

Semi-supervised node classification on graph-structured data has many ap...
02/10/2020

Bilinear Graph Neural Network with Neighbor Interactions

Graph Neural Network (GNN) is a powerful model to learn representations ...
07/27/2021

Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification

Node features and structural information of a graph are both crucial for...
06/18/2021

Being a Bit Frequentist Improves Bayesian Neural Networks

Despite their compelling theoretical properties, Bayesian neural network...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.