JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks

Abstract

Graph Convolutional Network (GCN) has exhibited strong empirical performance in many real-world applications. The vast majority of existing works on GCN primarily focus on the accuracy while ignoring how confident or uncertain a GCN is with respect to its predictions. Despite being a cornerstone of trustworthy graph mining, uncertainty quantification on GCN has not been well studied and the scarce existing efforts either fail to provide deterministic quantification or have to change the training procedure of GCN by introducing additional parameters or architectures. In this paper, we propose the first frequentist-based approach named JuryGCN in quantifying the uncertainty of GCN, where the key idea is to quantify the uncertainty of a node as the width of confidence interval by a jackknife estimator. Moreover, we leverage the influence functions to estimate the change in GCN parameters without re-training to scale up the computation. The proposed JuryGCN is capable of quantifying uncertainty deterministically without modifying the GCN architecture or introducing additional parameters. We perform extensive experimental evaluation on real-world datasets in the tasks of both active learning and semi-supervised node classification, which demonstrate the efficacy of the proposed method.

arXiv commentAccepted to KDD'22

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Neural Graph Collaborative Filtering
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Spectral Networks and Locally Connected Networks on Graphs
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Understanding Black-box Predictions via Influence Functions
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Predictive Uncertainty Estimation via Prior Networks
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• Active Learning for Graph Embedding
• RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network
• Graph Policy Network for Transferable Active Learning on Graphs
• Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions