mlsanityData to 14 Oct 2026

Nonparametric Teaching for Graph Property Learners

arXiv 2505.14170 ↗First posted 20 May 2025cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Inferring properties of graph-structured data, e.g., the solubility of molecules, essentially involves learning the implicit mapping from graphs to their properties. This learning process is often costly for graph property learners like Graph Convolutional Networks (GCNs). To address this, we propose a paradigm called Graph Neural Teaching (GraNT) that reinterprets the learning process through a novel nonparametric teaching perspective. Specifically, the latter offers a theoretical framework for teaching implicitly defined (i.e., nonparametric) mappings via example selection. Such an implicit mapping is realized by a dense set of graph-property pairs, with the GraNT teacher selecting a subset of them to promote faster convergence in GCN training. By analytically examining the impact of graph structure on parameter-based gradient descent during training, and recasting the evolution of GCNs--shaped by parameter updates--through functional gradient descent in nonparametric teaching, we show for the first time that teaching graph property learners (i.e., GCNs) is consistent with teaching structure-aware nonparametric learners. These new findings readily commit GraNT to enhancing learning efficiency of the graph property learner, showing significant reductions in training time for graph-level regression (-36.62%), graph-level classification (-38.19%), node-level regression (-30.97%) and node-level classification (-47.30%), all while maintaining its generalization performance.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 58 of its 81 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

58 of 81 references.

References · 58

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  8. 2021Convex optimizationcited by 2,515
  9. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  10. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  11. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  12. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
38 more
  1. 2019Simplifying Graph Convolutional Networkscited by 1,477
  2. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  3. 2016An overview of gradient descent optimization algorithmscited by 1,033
  4. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  5. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  6. 2019Graph Neural Networks for Social Recommendationcited by 714
  7. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  8. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  9. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
  10. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  11. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  12. 2015Coordinate Descent Algorithmscited by 219
  13. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 161
  14. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  15. 2017Stein Variational Gradient Descent as Gradient Flowcited by 152
  16. 2021Graph Learning: A Surveycited by 141
  17. 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 117
  18. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 96
  19. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  20. 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
  21. 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
  22. 2020On the Similarity between the Laplace and Neural Tangent Kernelscited by 76
  23. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  24. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 64
  25. 2018An Overview of Machine Teachingcited by 63
  26. 2017Iterative Machine Teachingcited by 41
  27. 2020Learning Graphons via Structured Gromov-Wasserstein Barycenterscited by 37
  28. 2023CopyRNeRF: Protecting the CopyRight of Neural Radiance Fieldscited by 34
  29. 2014Near-Optimally Teaching the Crowd to Classifycited by 32
  30. 2022Survey on Graph Neural Network Acceleration: An Algorithmic Perspectivecited by 26
  31. 2017Towards Black-box Iterative Machine Teachingcited by 20
  32. 2022Implicit Graphon Neural Representationcited by 19
  33. 2023A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardwarecited by 18
  34. 2023Graph Neural Tangent Kernel: Convergence on Large Graphscited by 16
  35. 2024Nonparametric Teaching of Implicit Neural Representationscited by 15
  36. 2019Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefitscited by 13
  37. 2018Unlearn What You Have Learned: Adaptive Crowd Teaching with Exponentially Decayed Memory Learnerscited by 11
  38. 2023Graph Sampling-based Meta-Learning for Molecular Property Predictioncited by 10

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

5 papers.

  1. 2025NTK-Guided Implicit Neural Teachingcited by 2
  2. 2026Nonparametric Teaching of Attention Learnerscited by 1
  3. 2025Large-Scale Bayesian Tensor Reconstruction via Approximate Message Passingcited by 0
  4. 2025Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modelingcited by 0
  5. 2026Model Evolution Under Zeroth-Order Optimization: A Neural Tangent Kernel Perspectivecited by 0