mlsanityData to 14 Oct 2026

Graph Lineages and Skeletal Graph Products

arXiv 2508.00197 ↗First posted 31 Jul 2025cs.CV cs.LG cs.NAcited by 0

Not on the map. Why?

Abstract (arXiv)

Graphs, and sequences of growing graphs, can be used to specify the architecture of mathematical models in many fields including machine learning and computational science. Here we define structured graph "lineages" (ordered by level number) that grow in a hierarchical fashion, so that: (1) the number of graph vertices and edges increases exponentially in level number; (2) bipartite graphs connect successive levels within a graph lineage and, as in multigrid methods, can constrain matrices relating successive levels; (3) using prolongation maps within a graph lineage, process-derived distance measures between graphs at successive levels can be defined; (4) a category of "graded graphs" can be defined, and using it low-cost "skeletal" variants of standard algebraic graph operations and type constructors (cross product, box product, disjoint sum, and function types) can be derived for graded graphs and hence hierarchical graph lineages; (5) these skeletal binary operators have similar but not identical algebraic and category-theoretic properties to their standard counterparts; (6) graph lineages and their skeletal product constructors can approach continuum limit objects. Additional space-efficient unary operators on graded graphs are also derived: thickening, which creates a graph lineage of multiscale graphs, and escalation to a graph lineage of search frontiers (useful as a generalization of adaptive grids and in defining "skeletal" functions). The result is an algebraic type theory for graded graphs and (hierarchical) graph lineages. The approach is expected to be well suited to defining hierarchical model architectures - "hierarchitectures" - and local sampling, search, or optimization algorithms on them. We demonstrate such application to deep neural networks (including visual and feature scale spaces) and to multigrid numerical methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 108 references that are in the map. First posted on arXiv 31 Jul 2025.

Builds on

52 of 108 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  6. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  7. 2015Automatic differentiation in machine learning: a surveycited by 855
  8. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  9. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  10. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 496
  11. 2017Progressive Neural Architecture Searchcited by 487
  12. 2018Invariant and Equivariant Graph Networkscited by 346
38 more
  1. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 322
  2. 2020Neural Architecture Search without Trainingcited by 244
  3. 2016Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivitycited by 138
  4. 2020From Local Structures to Size Generalization in Graph Neural Networkscited by 124
  5. 2019Deep Scale-spaces: Equivariance Over Scalecited by 114
  6. 2019B-Spline CNNs on Lie Groupscited by 97
  7. 2024Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equationscited by 91
  8. 2019A Step Toward Quantifying Independently Reproducible Machine Learning Researchcited by 77
  9. 2022Hierarchical Graph Transformer with Adaptive Node Samplingcited by 72
  10. 2017Parallel Multiscale Autoregressive Density Estimationcited by 71
  11. 2020Graph Structure of Neural Networkscited by 68
  12. 2018Modular Networks: Learning to Decompose Neural Computationcited by 62
  13. 2023Graph Metanetworks for Processing Diverse Neural Architecturescited by 57
  14. 2019Semi-Supervised Graph Classification: A Hierarchical Graph Perspectivecited by 55
  15. 2020Learning Algebraic Multigrid Using Graph Neural Networkscited by 54
  16. 2022Blending Neural Operators and Relaxation Methods in PDE Numerical Solverscited by 54
  17. 2017Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Studycited by 46
  18. 2021Categorical Foundations of Gradient-Based Learningcited by 44
  19. 2021Reinforcement Learning for Adaptive Mesh Refinementcited by 39
  20. 2020An Empirical Analysis of Backward Compatibility in Machine Learning Systemscited by 38
  21. 2024Position: Categorical Deep Learning is an Algebraic Theory of All Architecturescited by 32
  22. 2018Topological Approaches to Deep Learningcited by 29
  23. 2024Scale Equivariant Graph Metanetworkscited by 24
  24. 2017Deriving Neural Architectures from Sequence and Graph Kernelscited by 23
  25. 2017Peephole: Predicting Network Performance Before Trainingcited by 23
  26. 2020Model Assertions for Monitoring and Improving ML Modelscited by 22
  27. 2019Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filterscited by 18
  28. 2020A Functional Perspective on Learning Symmetric Functions with Neural Networkscited by 17
  29. 2021Learning optimal multigrid smoothers via neural networkscited by 17
  30. 2021Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scalescited by 17
  31. 2021Solving PDEs on Unknown Manifolds with Machine Learningcited by 12
  32. 2024Multiscale graph neural networks with adaptive mesh refinement for accelerating mesh-based simulationscited by 12
  33. 2018TAPAS: Train-less Accuracy Predictor for Architecture Searchcited by 11
  34. 2020Multiresolution Convolutional Autoencoderscited by 10
  35. 2023Gauge-equivariant neural networks as preconditioners in lattice QCDcited by 9
  36. 2020Geometrically Principled Connections in Graph Neural Networkscited by 8
  37. 2021Neural Network Layer Algebra: A Framework to Measure Capacity and Compression in Deep Learningcited by 2
  38. 2021Functorial String Diagrams for Reverse-Mode Automatic Differentiationcited by 2

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.