From Mice to Trains: Amortized Bayesian Inference on Graph Data
Not on the map. Why?
Abstract (arXiv)
Graphs arise across diverse domains, from biology and chemistry to social and information networks, as well as in transportation and logistics. Inference on graph-structured data requires methods that are permutation-invariant, scalable across varying sizes and sparsities, and capable of capturing complex long-range dependencies, making posterior estimation on graph parameters particularly challenging. Amortized Bayesian Inference (ABI) is a simulation-based framework that employs generative neural networks to enable fast, likelihood-free posterior inference. We adapt ABI to graph data to address these challenges to perform inference on node-, edge-, and graph-level parameters. Our approach couples permutation-invariant graph encoders with flexible neural posterior estimators in a two-module pipeline: a summary network maps attributed graphs to fixed-length representations, and an inference network approximates the posterior over parameters. In this setting, several neural architectures can serve as the summary network. In this work we evaluate multiple architectures and assess their performance on controlled synthetic settings and two real-world domains - biology and logistics - in terms of recovery and calibration.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 49 of its 79 references that are in the map. First posted on arXiv 5 Jan 2026.
Builds on
49 of 79 references.
References · 49
- 2017Attention Is All You Needcited by 59,932
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
- 2016Variational Inference: A Review for Statisticianscited by 1,466
- 2017Deep Setscited by 1,394
- 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
- 2020On Layer Normalization in the Transformer Architecturecited by 906
- 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
37 more
- 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
- 2019Are Sixteen Heads Really Better than One?cited by 803
- 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
- 2020A Generalization of Transformer Networks to Graphscited by 653
- 2019Neural Spline Flowscited by 590
- 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
- 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
- 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
- 2020A Note on Over-Smoothing for Graph Neural Networkscited by 245
- 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
- 2021Benchmarking Simulation-Based Inferencecited by 160
- 2018Inference Suboptimality in Variational Autoencoderscited by 131
- 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 118
- 2024All-in-one simulation-based inferencecited by 71
- 2022A Survey of Graph Neural Networks for Social Recommender Systemscited by 65
- 2020Talking-Heads Attentioncited by 57
- 2016Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimationcited by 50
- 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
- 2023BayesFlow: Amortized Bayesian Workflows With Neural Networkscited by 32
- 2021A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithfulcited by 27
- 2021Graphical Test for Discrete Uniformity and its Applications in Goodness of Fit Evaluation and Multiple Sample Comparisoncited by 26
- 2021Conditional Invertible Neural Networks for Diverse Image-to-Image Translationcited by 24
- 2016Deep Amortized Inference for Probabilistic Programscited by 22
- 2024Amortized Bayesian Experimental Design for Decision-Makingcited by 20
- 2022Simulation-Based Calibration Checking for Bayesian Computation: The Choice of Test Quantities Shapes Sensitivitycited by 19
- 2019Toward a principled Bayesian workflow in cognitive sciencecited by 16
- 2023Neural Bayes Estimators for Irregular Spatial Data using Graph Neural Networkscited by 13
- 2025Amortized In-Context Bayesian Posterior Estimationcited by 13
- 2024Amortized Bayesian Multilevel Modelscited by 12
- 2021Graph Representation Learning for Road Type Classificationcited by 8
- 2022Design Amortization for Bayesian Optimal Experimental Designcited by 7
- 2024Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and Benchmarkscited by 7
- 2021DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networkscited by 5
- 2018Amortized Bayesian inference for clustering modelscited by 2
- 2023Graph-informed simulation-based inference for models of active mattercited by 2
- 2024Testing and Improving the Robustness of Amortized Bayesian Inference for Cognitive Modelscited by 2
- 2025Uncertainty-Aware Surrogate-based Amortized Bayesian Inference for Computationally Expensive Modelscited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.