mlsanityData to 7 Oct 2026

Estimation of the Sample Frechet Mean: A Convolutional Neural Network Approach

arXiv 2210.07401 ↗First posted 13 Oct 2022cs.LG cs.SI physics.data-ancited by 0

Not on the map. Why?

Abstract (arXiv)

This work addresses the rising demand for novel tools in statistical and machine learning for "graph-valued random variables" by proposing a fast algorithm to compute the sample Frechet mean, which replaces the concept of sample mean for graphs (or networks). We use convolutional neural networks to learn the morphology of the graphs in a set of graphs. Our experiments on several ensembles of random graphs demonstrate that our method can reliably recover the sample Frechet mean.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 56 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

22 of 56 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  4. 2017Community Detection and Stochastic Block Modelscited by 317
  5. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 191
  6. 2018Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical propertiescited by 93
  7. 2020Wasserstein Embedding for Graph Learningcited by 56
  8. 2019Metrics for Graph Comparison: A Practitioner's Guidecited by 37
  9. 2014A Consistent Histogram Estimator for Exchangeable Graph Modelscited by 36
  10. 2022Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenterscited by 22
  11. 2013Network histograms and universality of blockmodel approximationcited by 20
  12. 2014Hypothesis Testing For Network Data in Functional Neuroimagingcited by 20
10 more
  1. 2015Discrete Wasserstein Barycenters: Optimal Transport for Discrete Datacited by 20
  2. 2019Modeling Network Populations via Graph Distancescited by 13
  3. 2020Randomised Wasserstein Barycenter Computation: Resampling with Statistical Guaranteescited by 8
  4. 2019Fr'echet Change Point Detectioncited by 5
  5. 2021Network Recovery from Unlabeled Noisy Samplescited by 5
  6. 2020node2coords: Graph Representation Learning with Wasserstein Barycenterscited by 4
  7. 2022Theoretical analysis and computation of the sample Frechet mean for sets of large graphs based on spectral informationcited by 2
  8. 2014An iterative step-function estimator for graphonscited by 1
  9. 2018Distributed Cartesian Power Graph Segmentation for Graphon Estimationcited by 1
  10. 2019Hausdorff and Wasserstein metrics on graphs and other structured datacited by 1

Built on by

Not cited yet.