Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The Manifold Scattering Transform for High-Dimensional Point Cloud Data (2206.10078v2)

Published 21 Jun 2022 in cs.LG, cs.NA, eess.SP, math.NA, and stat.ML

Abstract: The manifold scattering transform is a deep feature extractor for data defined on a Riemannian manifold. It is one of the first examples of extending convolutional neural network-like operators to general manifolds. The initial work on this model focused primarily on its theoretical stability and invariance properties but did not provide methods for its numerical implementation except in the case of two-dimensional surfaces with predefined meshes. In this work, we present practical schemes, based on the theory of diffusion maps, for implementing the manifold scattering transform to datasets arising in naturalistic systems, such as single cell genetics, where the data is a high-dimensional point cloud modeled as lying on a low-dimensional manifold. We show that our methods are effective for signal classification and manifold classification tasks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. The wave kernel signature: A quantum mechanical approach to shape analysis. In 2011 IEEE international conference on computer vision workshops (ICCV workshops), pp.  1626–1633. IEEE, 2011.
  2. Molecular graph generation via geometric scattering. arXiv preprint arXiv:2110.06241, 2021.
  3. FAUST: Dataset and evaluation for 3D mesh registration. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014.
  4. Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks. In Computer Graphics Forum, volume 34, pp.  13–23. Wiley Online Library, 2015.
  5. Learning shape correspondence with anisotropic convolutional neural networks. In Advances in Neural Information Processing Systems 29, pp. 3189–3197, 2016.
  6. Geometric deep learning: Going beyond Euclidean data. IEEE Signal Processing Magazine, 34(4):18–42, 2017.
  7. Spectral networks and deep locally connected networks on graphs. In International Conference on Learning Representations (ICLR), 2014.
  8. A cnn for homogneous riemannian manifolds with applications to neuroimaging. arXiv preprint arXiv:1805.05487, 2018.
  9. Manifoldnet: A deep neural network for manifold-valued data with applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.
  10. Convergence of graph Laplacian with kNN self-tuned kernels. Information and Inference: A Journal of the IMA, 09 2021a. ISSN 2049-8772. doi: 10.1093/imaiai/iaab019. URL https://doi.org/10.1093/imaiai/iaab019. iaab019.
  11. Eigen-convergence of gaussian kernelized graph laplacian by manifold heat interpolation. arXiv preprint arXiv:2101.09875, 2021b.
  12. Spherical cnns. In Proceedings of the 6th International Conference on Learning Representations, 2018.
  13. Diffusion maps. Applied and Computational Harmonic Analysis, 21:5–30, 2006.
  14. Diffusion wavelets. Applied and Computational Harmonic Analysis, 21(1):53–94, 2006.
  15. Spectral convergence of graph laplacian and heat kernel reconstruction in l∞\infty∞ from random samples. Applied and Computational Harmonic Analysis, 55:282–336, 2021. ISSN 1063-5203. doi: https://doi.org/10.1016/j.acha.2021.06.002. URL https://www.sciencedirect.com/science/article/pii/S1063520321000464.
  16. Stability of graph scattering transforms. In Advances in Neural Information Processing Systems 33, 2019a.
  17. Diffusion scattering transforms on graphs. In International Conference on Learning Representations, 2019b.
  18. Geometric scattering for graph data analysis. In Proceedings of the 36th International Conference on Machine Learning, PMLR, volume 97, pp.  2122–2131, 2019.
  19. Inductive representation learning on large graphs. Advances in neural information processing systems, 30, 2017.
  20. Wavelets on graphs via spectral graph theory. Applied and Computational Harmonic Analysis, 30:129–150, 2011.
  21. A riemannian network for spd matrix learning. In Thirty-First AAAI Conference on Artificial Intelligence, 2017.
  22. Building deep networks on grassmann manifolds. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.
  23. Pruned graph scattering transforms. In International Conference on Learning Representations, 2020.
  24. Semi-supervised classification with graph convolutional networks. Proc. of ICLR, 2016.
  25. On the generalization of equivariance and convolution in neural networks to the action of compact groups. arXiv:1802.03690, 2018.
  26. Kuchroo, M. et al. Multiscale phate identifies multimodal signatures of covid-19. Nature Biotechnology, 2022. ISSN 1546-1696. doi: 10.1038/s41587-021-01186-x.
  27. Transferability of spectral graph convolutional neural networks. Journal of Machine Learning Research, 22(272):1–59, 2021.
  28. Mallat, S. Recursive interferometric representations. In 18th European Signal Processing Conference (EUSIPCO-2010), Aalborg, Denmark, 2010.
  29. Mallat, S. Group invariant scattering. Communications on Pure and Applied Mathematics, 65(10):1331–1398, October 2012.
  30. Geodesic convolutional neural networks on riemannian manifolds. In IEEE International Conference on Computer Vision Workshop (ICCVW), 2015.
  31. Scattering networks on the sphere for scalable and rotationally equivariant spherical cnns. arXiv preprint arXiv:2102.02828, 2021.
  32. Can hybrid geometric scattering networks help solve the maximal clique problem?, 2022. URL https://arxiv.org/abs/2206.01506.
  33. Manifold learning-based methods for analyzing single-cell rna-sequencing data. Current Opinion in Systems Biology, 7:36–46, 2018.
  34. Spatio-temporal graph scattering transform. arXiv preprint arXiv:2012.03363, 2020.
  35. Understanding graph neural networks with asymmetric geometric scattering transforms. arXiv preprint arXiv:1911.06253, 2019.
  36. Geometric scattering networks on compact Riemannian manifolds. In Mathematical and Scientific Machine Learning Conference, 2020.
  37. 52 characterization of the tumor microenvironment in melanoma using multiplexed ion beam imaging (mibi). Journal for ImmunoTherapy of Cancer, 9(Suppl 2):A59–A59, 2021.
  38. Parallel transport convolution: Deformable convolutional networks on manifold-structured data. SIAM Journal on Imaging Sciences, 15(1):367–386, 2022.
  39. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine, 30(3):83–98, 2013.
  40. A concise and provably informative multi-scale signature based on heat diffusion. In Computer graphics forum, volume 28, pp.  1383–1392. Wiley Online Library, 2009.
  41. Unique signatures of histograms for local surface description. In European conference on computer vision, pp.  356–369, 2010.
  42. Data-driven learning of geometric scattering modules for gnns. In 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), pp.  1–6, 2021a. doi: 10.1109/MLSP52302.2021.9596169.
  43. Diffusion earth mover’s distance and distribution embeddings. In International Conference on Machine Learning, pp. 10336–10346. PMLR, 2021b.
  44. Graph attention networks. In International Conference on Learning Representations, 2018.
  45. Novel imaging revealing inner dynamics for cardiovascular waveform analysis via unsupervised manifold learning. Anesthesia & Analgesia, 130(5):1244–1254, 2020.
  46. Stability of manifold neural networks to deformations. arXiv preprint arXiv:2106.03725, 2021a.
  47. Stability of neural networks on manifolds to relative perturbations. arXiv preprint arXiv:2110.04702, 2021b.
  48. Overcoming oversmoothness in graph convolutional networks via hybrid scattering networks. arXiv preprint arXiv:2201.08932, 2022.
  49. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24, 2020.
  50. Self-tuning spectral clustering. Advances in neural information processing systems, 17, 2004.
  51. Graph convolutional neural networks via scattering. Applied and Computational Harmonic Analysis, 49(3)(3):1046–1074, 2019a.
  52. Encoding robust representation for graph generation. In International Joint Conference on Neural Networks, 2019b.
Citations (10)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now