mlsanityData to 14 Oct 2026

GraphPPD: Posterior Predictive Modelling for Graph-Level Inference

arXiv 2508.16995 ↗First posted 23 Aug 2025stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate modelling and quantification of predictive uncertainty is crucial in deep learning since it allows a model to make safer decisions when the data is ambiguous and facilitates the users' understanding of the model's confidence in its predictions. Along with the tremendously increasing research focus on graph neural networks (GNNs) in recent years, there have been numerous techniques which strive to capture the uncertainty in their predictions. However, most of these approaches are specifically designed for node or link-level tasks and cannot be directly applied to graph-level learning problems. In this paper, we propose a novel variational modelling framework for the posterior predictive distribution~(PPD) to obtain uncertainty-aware prediction in graph-level learning tasks. Based on a graph-level embedding derived from one of the existing GNNs, our framework can learn the PPD in a data-adaptive fashion. Experimental results on several benchmark datasets exhibit the effectiveness of our approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 69 references that are in the map. First posted on arXiv 23 Aug 2025.

Builds on

48 of 69 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  10. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  11. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  12. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
36 more
  1. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  2. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  3. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  4. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  5. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  6. 2020Benchmarking Graph Neural Networkscited by 680
  7. 2019Graph U-Netscited by 492
  8. 2021Rethinking Graph Transformers with Spectral Attentioncited by 473
  9. 2019Self-Attention Graph Poolingcited by 421
  10. 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
  11. 2021Transformers Can Do Bayesian Inferencecited by 360
  12. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  13. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 320
  14. 2018Neural Processescited by 311
  15. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
  16. 2019Attentive Neural Processescited by 283
  17. 2019ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representationscited by 156
  18. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 127
  19. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  20. 2019Fake News Detection on Social Media using Geometric Deep Learningcited by 118
  21. 2017Bayesian Compression for Deep Learningcited by 116
  22. 2018Meta-Learning Probabilistic Inference For Predictioncited by 110
  23. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 89
  24. 2017Geometric Matrix Completion with Recurrent Multi-Graph Neural Networkscited by 88
  25. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  26. 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
  27. 2015Bayesian Dark Knowledgecited by 45
  28. 2020Bootstrapping Neural Processescited by 40
  29. 2018Bayesian Semi-supervised Learning with Graph Gaussian Processescited by 28
  30. 2022Higher-order Clustering and Pooling for Graph Neural Networkscited by 26
  31. 2019A Flexible Generative Framework for Graph-based Semi-supervised Learningcited by 24
  32. 2021Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimationcited by 18
  33. 2022Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Designcited by 13
  34. 2020Non-Parametric Graph Learning for Bayesian Graph Neural Networkscited by 10
  35. 2019Graph Neural Processes: Towards Bayesian Graph Neural Networkscited by 6
  36. 2022The prediction of the quality of results in Logic Synthesis using Transformer and Graph Neural Networkscited by 1

Built on by

Not cited yet.