no code implementations • 1 May 2018 • Michael Eickenberg, Georgios Exarchakis, Matthew Hirn, Stéphane Mallat, Louis Thiry
We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory.
no code implementations • 29 Mar 2018 • Adam Gustafson, Matthew Hirn, Kitty Mohammed, Hariharan Narayanan, Jason Xu
Recently, the following smooth function approximation problem was proposed: given a finite set $E \subset \mathbb{R}^d$ and a function $f: E \rightarrow \mathbb{R}$, interpolate the given information with a function $\widehat{f} \in \dot{C}^{1, 1}(\mathbb{R}^d)$ (the class of first-order differentiable functions with Lipschitz gradients) such that $\widehat{f}(a) = f(a)$ for all $a \in E$, and the value of $\mathrm{Lip}(\nabla \widehat{f})$ is minimal.
no code implementations • 6 Feb 2015 • Matthew Hirn, Nicolas Poilvert, Stéphane Mallat
We present a novel approach to the regression of quantum mechanical energies based on a scattering transform of an intermediate electron density representation.
no code implementations • ICLR 2019 • Feng Gao, Guy Wolf, Matthew Hirn
We explore the generalization of scattering transforms from traditional (e. g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis.
no code implementations • 15 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.
no code implementations • NeurIPS 2017 • Michael Eickenberg, Georgios Exarchakis, Matthew Hirn, Stephane Mallat
We introduce a solid harmonic wavelet scattering representation, invariant to rigid motion and stable to deformations, for regression and classification of 2D and 3D signals.
no code implementations • ICLR 2019 • Feng Gao, Guy Wolf, Matthew Hirn
Furthermore, ConvNets inspired recent advances in geometric deep learning, which aim to generalize these networks to graph data by applying notions from graph signal processing to learn deep graph filter cascades.
no code implementations • 21 Nov 2018 • Xavier Brumwell, Paul Sinz, Kwang Jin Kim, Yue Qi, Matthew Hirn
Here this approach is extended for general steerable wavelets which are equivariant to translations and rotations, resulting in a sparse model of the target function.
no code implementations • 10 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.
no code implementations • 24 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.
no code implementations • 1 Jun 2020 • Paul Sinz, Michael W. Swift, Xavier Brumwell, Jialin Liu, Kwang Jin Kim, Yue Qi, Matthew Hirn
The dream of machine learning in materials science is for a model to learn the underlying physics of an atomic system, allowing it to move beyond interpolation of the training set to the prediction of properties that were not present in the original training data.
1 code implementation • 24 Sep 2019 • Matthew Hirn, Anna Little
After unbiasing the representation to remove the effects of the additive noise and random dilations, we recover an approximation of the power spectrum by solving a convex optimization problem, and thus reduce to a phase retrieval problem.
no code implementations • 22 May 2021 • Jieqian He, Matthew Hirn
We provide a new model for texture synthesis based on a multiscale, multilayer feature extractor.
no code implementations • 2 Jul 2021 • Matthew Hirn, Anna Little
We propose a method that recovers the power spectrum of the hidden signal by applying a data-driven, nonlinear unbiasing procedure, and thus the hidden signal is obtained up to an unknown phase.
no code implementations • 10 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.
no code implementations • 27 Oct 2021 • Renming Liu, Semih Cantürk, Frederik Wenkel, Dylan Sandfelder, Devin Kreuzer, Anna Little, Sarah McGuire, Leslie O'Bray, Michael Perlmutter, Bastian Rieck, Matthew Hirn, Guy Wolf, Ladislav Rampášek
Graph neural networks (GNNs) have attracted much attention due to their ability to leverage the intrinsic geometries of the underlying data.
no code implementations • 22 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.
no code implementations • 28 Mar 2022 • Guillaume Huguet, Alexander Tong, Bastian Rieck, Jessie Huang, Manik Kuchroo, Matthew Hirn, Guy Wolf, Smita Krishnaswamy
From a geometric perspective, we obtain convergence bounds based on the smallest transition probability and the radius of the data, whereas from a spectral perspective, our bounds are based on the eigenspectrum of the diffusion kernel.
no code implementations • 17 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.
no code implementations • 10 May 2023 • Sarah McGuire, Elizabeth Munch, Matthew Hirn
For deep learning problems on graph-structured data, pooling layers are important for down sampling, reducing computational cost, and to minimize overfitting.
no code implementations • 22 Feb 2024 • Liping Yin, Anna Little, Matthew Hirn
Motivated by modern data applications such as cryo-electron microscopy, the goal of classic multi-reference alignment (MRA) is to recover an unknown signal $f: \mathbb{R} \to \mathbb{R}$ from many observations that have been randomly translated and corrupted by additive noise.
1 code implementation • 14 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.
1 code implementation • 21 Jun 2022 • Joyce Chew, Holly R. Steach, Siddharth Viswanath, Hau-Tieng Wu, Matthew Hirn, Deanna Needell, Smita Krishnaswamy, Michael Perlmutter
The manifold scattering transform is a deep feature extractor for data defined on a Riemannian manifold.
1 code implementation • 16 May 2016 • Matthew Hirn, Stéphane Mallat, Nicolas Poilvert
Sparse scattering regressions give state of the art results over two databases of organic planar molecules.
1 code implementation • 15 Jun 2022 • Renming Liu, Semih Cantürk, Frederik Wenkel, Sarah McGuire, Xinyi Wang, Anna Little, Leslie O'Bray, Michael Perlmutter, Bastian Rieck, Matthew Hirn, Guy Wolf, Ladislav Rampášek
Graph Neural Networks (GNNs) extend the success of neural networks to graph-structured data by accounting for their intrinsic geometry.
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.
1 code implementation • 15 Sep 2021 • Renming Liu, Matthew Hirn, Arjun Krishnan
$\textit{Node2vec}$ is a widely used method for node embedding that works by exploring the local neighborhoods via biased random walks on the graph.