mlsanityData to 14 Oct 2026

Fast and Deep Graph Neural Networks

arXiv 1911.08941 ↗First posted 20 Nov 2019cs.LG math.DS stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

We address the efficiency issue for the construction of a deep graph neural network (GNN). The approach exploits the idea of representing each input graph as a fixed point of a dynamical system (implemented through a recurrent neural network), and leverages a deep architectural organization of the recurrent units. Efficiency is gained by many aspects, including the use of small and very sparse networks, where the weights of the recurrent units are left untrained under the stability condition introduced in this work. This can be viewed as a way to study the intrinsic power of the architecture of a deep GNN, and also to provide insights for the set-up of more complex fully-trained models. Through experimental results, we show that even without training of the recurrent connections, the architecture of small deep GNN is surprisingly able to achieve or improve the state-of-the-art performance on a significant set of tasks in the field of graphs classification.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 12; 2023: 7; 2024: 4; 2025: 3; 2026: 1.

35 papers.

Sort:

  1. 2022ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networkscited by 31
  2. 2022Optimization-Induced Graph Implicit Nonlinear Diffusioncited by 28
  3. 2021VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queriescited by 19
  4. 2022MGNNI: Multiscale Graph Neural Networks with Implicit Layerscited by 19
  5. 2022Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Surveycited by 14
  6. 2022Leave Graphs Alone: Addressing Over-Squashing without Rewiringcited by 14
  7. 2024Topology-aware Embedding Memory for Continual Learning on Expanding Networkscited by 14
  8. 2021Implicit vs Unfolded Graph Neural Networkscited by 13
  9. 2021Convergent Graph Solverscited by 12
  10. 2022Transforming PageRank into an Infinite-Depth Graph Neural Networkcited by 11
  11. 2021Pyramidal Reservoir Graph Neural Networkcited by 10
  12. 2022Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approachcited by 8
23 more
  1. 2021Continuous-Depth Neural Models for Dynamic Graph Predictioncited by 7
  2. 2022Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representationscited by 7
  3. 2021Dynamic Graph Echo State Networkscited by 6
  4. 2023Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detectioncited by 6
  5. 2024Training-free Graph Neural Networks and the Power of Labels as Featurescited by 5
  6. 2022Binary Graph Convolutional Network with Capacity Explorationcited by 4
  7. 2023What Do GNNs Actually Learn? Towards Understanding their Representationscited by 4
  8. 2023Addressing Heterophily in Node Classification with Graph Echo State Networkscited by 4
  9. 2023Edge of stability echo state networkscited by 4
  10. 2021Permute Me Softly: Learning Soft Permutations for Graph Representationscited by 3
  11. 2024IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networkscited by 3
  12. 2022Beyond Homophily with Graph Echo State Networkscited by 2
  13. 2023An Empirical Evaluation of Rewiring Approaches in Graph Neural Networkscited by 2
  14. 2025Rapid training of Hamiltonian graph networks using random featurescited by 2
  15. 2025Adaptive Initial Residual Connections for GNNs with Theoretical Guaranteescited by 2
  16. 2022Euler State Networks: Non-dissipative Reservoir Computingcited by 1
  17. 2023Modeling Edge Features with Deep Bayesian Graph Networkscited by 1
  18. 2025Efficient quantification on large-scale networkscited by 1
  19. 2021Phase Transition Adaptationcited by 0
  20. 2022Density-Aware Hyper-Graph Neural Networks for Graph-based Semi-supervised Node Classificationcited by 0
  21. 2023Provably Convergent Subgraph-wise Sampling for Fast GNN Trainingcited by 0
  22. 2024Graph in Graph Neural Networkcited by 0
  23. 2026Reservoir-Based Graph Convolutional Networkscited by 0