Search Results for author: Michael Perlmutter

Found 21 papers, 7 papers with code

Bayesian Formulations for Graph Spectral Denoising

no code implementations27 Nov 2023 Sam Leone, Xingzhi Sun, Michael Perlmutter, Smita Krishnaswamy

In particular, we present algorithms for the cases where the signal is perturbed by Gaussian noise, dropout, and uniformly distributed noise.

Denoising

BLIS-Net: Classifying and Analyzing Signals on Graphs

no code implementations26 Oct 2023 Charles Xu, Laney Goldman, Valentina Guo, Benjamin Hollander-Bodie, Maedee Trank-Greene, Ian Adelstein, Edward De Brouwer, Rex Ying, Smita Krishnaswamy, Michael Perlmutter

We make several crucial changes to the original geometric scattering architecture which we prove increase the ability of our network to capture information about the input signal and show that BLIS-Net achieves superior performance on both synthetic and real-world data sets based on traffic flow and fMRI data.

Graph Classification Node Classification

Graph topological property recovery with heat and wave dynamics-based features on graphs

no code implementations18 Sep 2023 Dhananjay Bhaskar, Yanlei Zhang, Charles Xu, Xingzhi Sun, Oluwadamilola Fasina, Guy Wolf, Maximilian Nickel, Michael Perlmutter, Smita Krishnaswamy

In this paper, we propose Graph Differential Equation Network (GDeNet), an approach that harnesses the expressive power of solutions to PDEs on a graph to obtain continuous node- and graph-level representations for various downstream tasks.

A Flow Artist for High-Dimensional Cellular Data

no code implementations31 Jul 2023 Kincaid MacDonald, Dhananjay Bhaskar, Guy Thampakkul, Nhi Nguyen, Joia Zhang, Michael Perlmutter, Ian Adelstein, Smita Krishnaswamy

Existing embedding techniques either do not utilize velocity information or embed the coordinates and velocities independently, i. e., they either impose velocities on top of an existing point embedding or embed points within a prescribed vector field.

Manifold Filter-Combine Networks

1 code implementation8 Jul 2023 Joyce Chew, Edward De Brouwer, Smita Krishnaswamy, Deanna Needell, Michael Perlmutter

We introduce a class of manifold neural networks (MNNs) that we call Manifold Filter-Combine Networks (MFCNs), that aims to further our understanding of MNNs, analogous to how the aggregate-combine framework helps with the understanding of graph neural networks (GNNs).

A Convergence Rate for Manifold Neural Networks

no code implementations23 Dec 2022 Joyce Chew, Deanna Needell, Michael Perlmutter

Moreover, in this work, the authors provide a numerical scheme for implementing such neural networks when the manifold is unknown and one only has access to finitely many sample points.

Geometric Scattering on Measure Spaces

no code implementations17 Aug 2022 Joyce Chew, Matthew Hirn, Smita Krishnaswamy, Deanna Needell, Michael Perlmutter, Holly Steach, Siddharth Viswanath, Hau-Tieng Wu

Our proposed framework includes previous work on geometric scattering as special cases but also applies to more general settings such as directed graphs, signed graphs, and manifolds with boundary.

Learnable Filters for Geometric Scattering Modules

no code implementations15 Aug 2022 Alexander Tong, Frederik Wenkel, Dhananjay Bhaskar, Kincaid MacDonald, Jackson Grady, Michael Perlmutter, Smita Krishnaswamy, Guy Wolf

We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters.

Descriptive Graph Classification

Can Hybrid Geometric Scattering Networks Help Solve the Maximum Clique Problem?

1 code implementation3 Jun 2022 Yimeng Min, Frederik Wenkel, Michael Perlmutter, Guy Wolf

We propose a geometric scattering-based graph neural network (GNN) for approximating solutions of the NP-hard maximum clique (MC) problem.

Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks

no code implementations22 Jan 2022 Frederik Wenkel, Yimeng Min, Matthew Hirn, Michael Perlmutter, Guy Wolf

We further introduce an attention framework that allows the model to locally attend over combined information from different filters at the node level.

A Hybrid Scattering Transform for Signals with Isolated Singularities

no code implementations10 Oct 2021 Michael Perlmutter, Jieqian He, Mark Iwen, Matthew Hirn

We also show that the Gabor measurements used in the second layer can be used to synthesize sparse signals such as those produced by the first layer.

On audio enhancement via online non-negative matrix factorization

1 code implementation7 Oct 2021 Andrew Sack, Wenzhao Jiang, Michael Perlmutter, Palina Salanevich, Deanna Needell

We propose a method for noise reduction, the task of producing a clean audio signal from a recording corrupted by additive noise.

Denoising

MagNet: A Neural Network for Directed Graphs

1 code implementation NeurIPS 2021 Xitong Zhang, Yixuan He, Nathan Brugnone, Michael Perlmutter, Matthew Hirn

In this paper, we propose MagNet, a spectral GNN for directed graphs based on a complex Hermitian matrix known as the magnetic Laplacian.

Link Prediction Node Classification

Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms

1 code implementation14 Nov 2019 Michael Perlmutter, Alexander Tong, Feng Gao, Guy Wolf, Matthew Hirn

As a result, the proposed construction unifies and extends known theoretical results for many of the existing graph scattering architectures.

Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds

no code implementations24 May 2019 Michael Perlmutter, Feng Gao, Guy Wolf, Matthew Hirn

The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks.

Translation

Scattering Statistics of Generalized Spatial Poisson Point Processes

no code implementations10 Feb 2019 Michael Perlmutter, Jieqian He, Matthew Hirn

We present a machine learning model for the analysis of randomly generated discrete signals, modeled as the points of an inhomogeneous, compound Poisson point process.

Point Processes

Geometric Scattering on Manifolds

no code implementations15 Dec 2018 Michael Perlmutter, Guy Wolf, Matthew Hirn

The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of the success of convolutional neural networks (ConvNets) in image data analysis and other tasks.

Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.