mlsanityData to 14 Oct 2026

SWING: Unlocking Implicit Graph Representations for Graph Random Features

arXiv 2602.12703 ↗First posted 13 Feb 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose SWING: Space Walks for Implicit Network Graphs, a new class of algorithms for computations involving Graph Random Features on graphs given by implicit representations (i-graphs), where edge-weights are defined as bi-variate functions of feature vectors in the corresponding nodes. Those classes of graphs include several prominent examples, such as: ε-neighborhood graphs, used on regular basis in machine learning. Rather than conducting walks on graphs' nodes, those methods rely on walks in continuous spaces, in which those graphs are embedded. To accurately and efficiently approximate original combinatorial calculations, SWING applies customized Gumbel-softmax sampling mechanism with linearized kernels, obtained via random features coupled with importance sampling techniques. This algorithm is of its own interest. SWING relies on the deep connection between implicitly defined graphs and Fourier analysis, presented in this paper. SWING is accelerator-friendly and does not require input graph materialization. We provide detailed analysis of SWING and complement it with thorough experiments on different classes of i-graphs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 49 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

19 of 49 references.

References · 19

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  3. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 183
  4. 2016Orthogonal Random Featurescited by 91
  5. 2024On the Scalability of GNNs for Molecular Graphscited by 36
  6. 2021Efficient and Interpretable Robot Manipulation with Graph Neural Networkscited by 22
  7. 2023Taming graph kernels with random featurescited by 17
  8. 2017Stability of the Lanczos Method for Matrix Function Approximationcited by 16
  9. 2022Molecule Generation for Drug Design: a Graph Learning Perspectivecited by 13
  10. 2022MolE: a molecular foundation model for drug discoverycited by 12
  11. 2023General Graph Random Featurescited by 10
  12. 2023Simplex Random Featurescited by 9
7 more
  1. 2021Large sample spectral analysis of graph-based multi-manifold clusteringcited by 8
  2. 2023Efficient Graph Field Integrators Meet Point Cloudscited by 7
  3. 2024Linear Transformer Topological Masking with Graph Random Featurescited by 7
  4. 2025Graph Random Features for Scalable Gaussian Processescited by 5
  5. 2024Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphscited by 3
  6. 2025Computationally-efficient Graph Modeling with Refined Graph Random Featurescited by 2
  7. 2023Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolutioncited by 1

Built on by

Not cited yet.