mlsanityData to 7 Oct 2026

Training-free Graph Neural Networks and the Power of Labels as Features

arXiv 2404.19288 ↗First posted 30 Apr 2024cs.LG cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 51 of its 59 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

51 of 59 references.

References · 51

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  8. 2017Mixed Precision Trainingcited by 1,135
  9. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  10. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  11. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  12. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
38 more
  1. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  2. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  3. 2020Simple and Deep Graph Convolutional Networkscited by 857
  4. 2019Graph Neural Networks for Social Recommendationcited by 711
  5. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  6. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  7. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  8. 2020What is the State of Neural Network Pruning?cited by 578
  9. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  10. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  12. 2019Provably Powerful Graph Networkscited by 385
  13. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 342
  14. 2018Invariant and Equivariant Graph Networkscited by 339
  15. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  16. 2019What graph neural networks cannot learn: depth vs widthcited by 195
  17. 2020Random Features Strengthen Graph Neural Networkscited by 184
  18. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 183
  19. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  20. 2019Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networkscited by 177
  21. 2018Training Deep Neural Networks with 8-bit Floating Point Numberscited by 163
  22. 2019Relational Pooling for Graph Representationscited by 150
  23. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 150
  24. 2019Knowledge Graph Convolutional Networks for Recommender Systemscited by 121
  25. 2023Rethinking the Expressive Power of GNNs via Graph Biconnectivitycited by 119
  26. 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
  27. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 95
  28. 2019Approximation Ratios of Graph Neural Networks for Combinatorial Problemscited by 68
  29. 2018GeniePath: Graph Neural Networks with Adaptive Receptive Pathscited by 66
  30. 2023Graph Neural Prompting with Large Language Modelscited by 64
  31. 2022Theory of Graph Neural Networks: Representation and Learningcited by 60
  32. 2019Estimating Node Importance in Knowledge Graphs Using Graph Neural Networkscited by 43
  33. 2021Bag of Tricks for Node Classification with Graph Neural Networkscited by 40
  34. 2019Fast and Deep Graph Neural Networkscited by 35
  35. 2021Large-scale graph representation learning with very deep GNNs and self-supervisioncited by 18
  36. 2021Why Propagate Alone? Parallel Use of Labels and Features on Graphscited by 9
  37. 2019Constant Time Graph Neural Networkscited by 4
  38. 2023Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structurecited by 4

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 0; 2026: 2.

5 papers.

  1. 2024Fully-inductive Node Classification on Arbitrary Graphscited by 36
  2. 2024Revisiting Random Walks for Learning on Graphscited by 13
  3. 2026Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priorscited by 10
  4. 2024Link Prediction with Untrained Message Passing Layerscited by 3
  5. 2026Ftextsuperscript2LP-AP: Fast & Flexible Label Propagation with Adaptive Propagation Kernelcited by 0