mlsanityData to 7 Oct 2026

Stochastic Aggregation in Graph Neural Networks

arXiv 2102.12648 ↗First posted 25 Feb 2021stat.ML cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited discriminating power as a result of suboptimally expressive aggregating mechanisms. We herein present a unifying framework for stochastic aggregation (STAG) in GNNs, where noise is (adaptively) injected into the aggregation process from the neighborhood to form node embeddings. We provide theoretical arguments that STAG models, with little overhead, remedy both of the aforementioned problems. In addition to fixed-noise models, we also propose probabilistic versions of STAG models and a variational inference framework to learn the noise posterior. We conduct illustrative experiments clearly targeting oversmoothing and multiset aggregation limitations. Furthermore, STAG enhances general performance of GNNs demonstrated by competitive performance in common citation and molecule graph benchmark datasets.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 25 Feb 2021.

Builds on

19 of 31 references.

References · 19

  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. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2016Variational Inference: A Review for Statisticianscited by 1,466
  10. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  11. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  12. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
7 more
  1. 2015Weight Uncertainty in Neural Networkscited by 554
  2. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  3. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  4. 2020A Note on Over-Smoothing for Graph Neural Networkscited by 245
  5. 2018Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputscited by 96
  6. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 88
  7. 2019Graph Neural Networks Exponentially Lose Expressive Power for Node Classificationcited by 16

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 1; 2024: 3; 2025: 1.

6 papers.

  1. 2024Non-convolutional Graph Neural Networkscited by 11
  2. 2021Adaptive Neural Message Passing for Inductive Learning on Hypergraphscited by 10
  3. 2023Machine-learned molecular mechanics force field for the simulation of protein-ligand systems and beyondcited by 5
  4. 2024On the design space between molecular mechanics and machine learning force fieldscited by 3
  5. 2024Molecular Dynamics and Machine Learning Unlock Possibilities in Beauty Design -- A Perspectivecited by 1
  6. 2025Integrating Causality with Neurochaos Learning: Proposed Approach and Research Agendacited by 0