Convolutional neural networks (CNNs) are revolutionizing imaging science for two- and three-dimensional images over Euclidean domains. However, many data sets are intrinsically non-Euclidean and are better modeled through other mathematical structures, such as graphs or manifolds. This state of affairs has led to the development of geometric deep learning, which refers to a body of research that aims to translate the principles of CNNs to these non-Euclidean structures. In the process, various challenges have arisen, including how to define such geometric networks, how to compute and train them efficiently, and what are their mathematical properties.
In this letter we describe the geometric wavelet scattering transform, which is a type of geometric CNN for graphs and manifolds consisting of alternating multiscale geometric wavelet transforms and nonlinear activation functions. As the name suggests, the geometric wavelet scattering transform is an adaptation of the Euclidean wavelet scattering transform, first introduced by S. Mallat, to graph and manifold data. Like its Euclidean counterpart, the geometric wavelet scattering transform has several desirable properties. In the manifold setting these properties include isometric invariance up to a user specified scale and stability to small diffeomorphisms. Numerical results on manifold and graph data sets, including graph and manifold classification tasks as well as others, illustrate the practical utility of the approach.
more »
« less
The manifold scattering transform for high-dimensional point cloud data
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.
more »
« less
- Award ID(s):
- 2047856
- NSF-PAR ID:
- 10434228
- Date Published:
- Journal Name:
- Proceedings of Machine Learning Research
- Volume:
- 196
- ISSN:
- 2640-3498
- Page Range / eLocation ID:
- 67-78
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Since the cost of labeling data is getting higher and higher, we hope to make full use of the large amount of unlabeled data and improve image classification effect through adding some unlabeled samples for training. In addition, we expect to uniformly realize two tasks, namely the clustering of the unlabeled data and the recognition of the query image. We achieve the goal by designing a novel sparse model based on manifold assumption, which has been proved to work well in many tasks. Based on the assumption that images of the same class lie on a sub-manifold and an image can be approximately represented as the linear combination of its neighboring data due to the local linear property of manifold, we proposed a sparse representation model on manifold. Specifically, there are two regularizations, i.e., a variant Trace lasso norm and the manifold Laplacian regularization. The first regularization term enables the representation coefficients satisfying sparsity between groups and density within a group. And the second term is manifold Laplacian regularization by which label can be accurately propagated from labeled data to unlabeled data. Augmented Lagrange Multiplier (ALM) scheme and Gauss Seidel Alternating Direction Method of Multiplier (GS-ADMM) are given to solve the problem numerically. We conduct some experiments on three human face databases and compare the proposed work with several state-of-the-art methods. For each subject, some labeled face images are randomly chosen for training for those supervised methods, and a small amount of unlabeled images are added to form the training set of the proposed approach. All experiments show our method can get better classification results due to the addition of unlabeled samples.more » « less
-
Lu, Jianfeng ; Ward, Rachel (Ed.)The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks. Inspired by recent interest in geometric deep learning, which aims to generalize convolutional neural networks to manifold and graph-structured domains, we define a geometric scattering transform on manifolds. Similar to the Euclidean scattering transform, the geometric scattering transform is based on a cascade of wavelet filters and pointwise nonlinearities. It is invariant to local isometries and stable to certain types of diffeomorphisms. Empirical results demonstrate its utility on several geometric learning tasks. Our results generalize the deformation stability and local translation invariance of Euclidean scattering, and demonstrate the importance of linking the used filter structures to the underlying geometry of the data.more » « less
-
more » « less
Abstract Optimal transport (OT) methods seek a transformation map (or plan) between two probability measures, such that the transformation has the minimum transportation cost. Such a minimum transport cost, with a certain power transform, is called the Wasserstein distance. Recently, OT methods have drawn great attention in statistics, machine learning, and computer science, especially in deep generative neural networks. Despite its broad applications, the estimation of high‐dimensional Wasserstein distances is a well‐known challenging problem owing to the curse‐of‐dimensionality. There are some cutting‐edge projection‐based techniques that tackle high‐dimensional OT problems. Three major approaches of such techniques are introduced, respectively, the slicing approach, the iterative projection approach, and the projection robust OT approach. Open challenges are discussed at the end of the review.
This article is categorized under:
Statistical and Graphical Methods of Data Analysis > Dimension Reduction
Statistical Learning and Exploratory Methods of the Data Sciences > Manifold Learning
-
We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution ρ in ℝD, that is nearly supported on a d-dimensional set - for example supported on a d-dimensional manifold. Geometric Multi-Resolution Analysis (GMRA) provides a robust and computationally efficient procedure to construct low-dimensional geometric approximations of at varying resolutions. We introduce GMRA approximations that adapt to the unknown regularity of , by introducing a thresholding algorithm on the geometric wavelet coefficients. We show that these data-driven, empirical geometric approximations perform well, when the threshold is chosen as a suitable universal function of the number of samples n, on a large class of measures ρ, that are allowed to exhibit different regularity at different scales and locations, thereby efficiently encoding data from more complex measures than those supported on manifolds. These GMRA approximations are associated to a dictionary, together with a fast transform mapping data to d-dimensional coefficients, and an inverse of such a map, all of which are data-driven. The algorithms for both the dictionary construction and the transforms have complexity CDnlogn with the constant C exponential in d. Our work therefore establishes Adaptive GMRA as a fast dictionary learning algorithm, with approximation guarantees, for intrinsically low-dimensional data. We include several numerical experiments on both synthetic and real data, confirming our theoretical results and demonstrating the effectiveness of Adaptive GMRA.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
