mlsanityData to 14 Oct 2026

Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks

arXiv 2305.10544 ↗First posted 17 May 2023cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

We introduce Graph-Induced Sum-Product Networks (GSPNs), a new probabilistic framework for graph representation learning that can tractably answer probabilistic queries. Inspired by the computational trees induced by vertices in the context of message-passing neural networks, we build hierarchies of sum-product networks (SPNs) where the parameters of a parent SPN are learnable transformations of the a-posterior mixing probabilities of its children's sum units. Due to weight sharing and the tree-shaped computation graphs of GSPNs, we obtain the efficiency and efficacy of deep graph networks with the additional advantages of a probabilistic model. We show the model's competitiveness on scarce supervision scenarios, under missing data, and for graph classification in comparison to popular neural models. We complement the experiments with qualitative analyses on hyper-parameters and the model's ability to answer probabilistic queries.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

38 of 72 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2017Deep Setscited by 1,421
  10. 2016Variational Graph Auto-Encoderscited by 1,382
  11. 2018Deep Graph Infomaxcited by 1,106
  12. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
26 more
  1. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  2. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  3. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  4. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  5. 2018Deep Learning on Graphs: A Surveycited by 393
  6. 2016Learning Convolutional Neural Networks for Graphscited by 314
  7. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  8. 2015Highway Networkscited by 260
  9. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 260
  10. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  11. 2019A Gentle Introduction to Deep Learning for Graphscited by 108
  12. 2013A Differential Approach to Inference in Bayesian Networkscited by 93
  13. 2019GMNN: Graph Markov Neural Networkscited by 82
  14. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 63
  15. 2020ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Predictioncited by 58
  16. 2022GraphWorld: Fake Graphs Bring Real Insights for GNNscited by 56
  17. 2020Graph Convolutional Networks for Graphs Containing Missing Featurescited by 47
  18. 2020Learning on Attribute-Missing Graphscited by 42
  19. 2016On the Latent Variable Interpretation in Sum-Product Networkscited by 40
  20. 2019Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architecturescited by 24
  21. 2019Bayesian Learning of Sum-Product Networkscited by 24
  22. 2016Visualizing and Understanding Sum-Product Networkscited by 18
  23. 2019Gradient-based training of Gaussian Mixture Models for High-Dimensional Streaming Datacited by 13
  24. 2018Automatic Bayesian Density Analysiscited by 10
  25. 2018Learning Representations of Missing Data for Predicting Patient Outcomescited by 6
  26. 2017Growing Attributed Networks through Local Processescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 1.

7 papers.

  1. 2023Cooperative Graph Neural Networkscited by 36
  2. 2025Tractable Representation Learning with Probabilistic Circuitscited by 4
  3. 2024Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphscited by 3
  4. 2024GraphSPNs: Sum-Product Networks Benefit From Canonical Orderingscited by 2
  5. 2025Early-Exit Graph Neural Networkscited by 2
  6. 2026Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solutioncited by 2
  7. 2025Probabilistic Graph Circuits: Deep Generative Models for Tractable Probabilistic Inference over Graphscited by 1