mlsanityData to 7 Oct 2026

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

arXiv 2210.15575 ↗First posted 27 Oct 2022cs.LG cs.AI stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Current graph neural networks (GNNs) that tackle node classification on graphs tend to only focus on nodewise scores and are solely evaluated by nodewise metrics. This limits uncertainty estimation on graphs since nodewise marginals do not fully characterize the joint distribution given the graph structure. In this work, we propose novel edgewise metrics, namely the edgewise expected calibration error (ECE) and the agree/disagree ECEs, which provide criteria for uncertainty estimation on graphs beyond the nodewise setting. Our experiments demonstrate that the proposed edgewise metrics can complement the nodewise results and yield additional insights. Moreover, we show that GNN models which consider the structured prediction problem on graphs tend to have better uncertainty estimations, which illustrates the benefit of going beyond the nodewise setting.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

20 of 32 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  7. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  8. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  9. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  10. 2019Verified Uncertainty Calibrationcited by 307
  11. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  12. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
8 more
  1. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 88
  2. 2019GMNN: Graph Markov Neural Networkscited by 82
  3. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  4. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  5. 2013Loopy Belief Propagation for Approximate Inference: An Empirical Studycited by 76
  6. 2022What Makes Graph Neural Networks Miscalibrated?cited by 39
  7. 2019Are Graph Neural Networks Miscalibrated?cited by 14
  8. 2021Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classificationcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 1.

6 papers.

  1. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  2. 2023SimCalib: Graph Neural Network Calibration based on Similarity between Nodescited by 10
  3. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  4. 2025Structural Alignment Improves Graph Test-Time Adaptationcited by 2
  5. 2023Population-wise Labeling of Sulcal Graphs using Multi-graph Matchingcited by 1
  6. 2024Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategycited by 1