Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
arXiv:2110.14012
Abstract
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.
Neurips 2021
References in corpus (25)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Variational Inference with Normalizing Flows
- Fast Graph Representation Learning with PyTorch Geometric
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Pitfalls of Graph Neural Network Evaluation
- Evidential Deep Learning to Quantify Classification Uncertainty
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning
- Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
- Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
- Uncertainty-based Continual Learning with Adaptive Regularization
- Unifying Graph Convolutional Neural Networks and Label Propagation
- BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
- Contrastive Training for Improved Out-of-Distribution Detection
- Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
- Sufficient Conditions for Idealised Models to Have No Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks
- Perfect density models cannot guarantee anomaly detection
- Uncertainty quantification of molecular property prediction with Bayesian neural networks
- Bayesian Graph Convolutional Neural Networks using Node Copying
- Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
- Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
- Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks
- I-GCN: Robust Graph Convolutional Network via Influence Mechanism