no code implementations • 19 Nov 2024 • Elliott Abel, Andrew J. Steindl, Selma Mazioud, Ellie Schueler, Folu Ogundipe, Ellen Zhang, Yvan Grinspan, Kristof Reimann, Peyton Crevasse, Dhananjay Bhaskar, Siddharth Viswanath, Yanlei Zhang, Tim G. J. Rudner, Ian Adelstein, Smita Krishnaswamy
Drawing motivation from the manifold hypothesis, which posits that most high-dimensional data lies on or near low-dimensional manifolds, we apply manifold learning to the space of neural networks.
1 code implementation • 27 Oct 2024 • Siddharth Viswanath, Dhananjay Bhaskar, David R. Johnson, Joao Felipe Rocha, Egbert Castro, Jackson D. Grady, Alex T. Grigas, Michael A. Perlmutter, Corey S. O'Hern, Smita Krishnaswamy
Understanding the dynamic nature of protein structures is essential for comprehending their biological functions.
1 code implementation • 18 Oct 2024 • David R. Johnson, Joyce Chew, Siddharth Viswanath, Edward De Brouwer, Deanna Needell, Smita Krishnaswamy, Michael Perlmutter
In order to better understand manifold neural networks (MNNs), we introduce Manifold Filter-Combine Networks (MFCNs).
no code implementations • 16 Oct 2024 • Xingzhi Sun, Danqi Liao, Kincaid MacDonald, Yanlei Zhang, Chen Liu, Guillaume Huguet, Guy Wolf, Ian Adelstein, Tim G. J. Rudner, Smita Krishnaswamy
GAGA constructs a neural network embedding space that respects the intrinsic geometries discovered by manifold learning and learns a novel warped Riemannian metric on the data space.
1 code implementation • 4 Oct 2024 • Chen Liu, Danqi Liao, Alejandro Parada-Mayorga, Alejandro Ribeiro, Marcello DiStasio, Smita Krishnaswamy
The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for biomedical research and clinical diagnostics.
no code implementations • 27 Sep 2024 • Arman Afrasiyabi, Dhananjay Bhaskar, Erica L. Busch, Laurent Caplette, Rahul Singh, Guillaume Lajoie, Nicholas B. Turk-Browne, Smita Krishnaswamy
Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordings such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which have increased spatial precision.
no code implementations • 27 Sep 2024 • Arman Afrasiyabi, Erica Busch, Rahul Singh, Dhananjay Bhaskar, Laurent Caplette, Nicholas Turk-Browne, Smita Krishnaswamy
In this work, we explore the decoding of mental imagery from subjects using their fMRI measurements.
1 code implementation • 14 Sep 2024 • Xingzhi Sun, Charles Xu, João F. Rocha, Chen Liu, Benjamin Hollander-Bodie, Laney Goldman, Marcello DiStasio, Michael Perlmutter, Smita Krishnaswamy
In many data-driven applications, higher-order relationships among multiple objects are essential in capturing complex interactions.
2 code implementations • 20 Jun 2024 • Chen Liu, Ke Xu, Liangbo L. Shen, Guillaume Huguet, Zilong Wang, Alexander Tong, Danilo Bzdok, Jay Stewart, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy
We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods.
1 code implementation • 4 Dec 2023 • Danqi Liao, Chen Liu, Benjamin W. Christensen, Alexander Tong, Guillaume Huguet, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to compute reliably in high dimensions.
no code implementations • 27 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.
no code implementations • 26 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.
no code implementations • 18 Sep 2023 • Dhananjay Bhaskar, Yanlei Zhang, Charles Xu, Xingzhi Sun, Oluwadamilola Fasina, Guy Wolf, Maximilian Nickel, Michael Perlmutter, Smita Krishnaswamy
In this paper we introduce DYMAG: a message passing paradigm for GNNs built on the expressive power of continuous, multiscale graph-dynamics.
no code implementations • 14 Sep 2023 • Aarthi Venkat, Joyce Chew, Ferran Cardoso Rodriguez, Christopher J. Tape, Michael Perlmutter, Smita Krishnaswamy
We show this method outperforms numerous others on tasks such as embedding directed graphs and learning cellular signaling networks.
no code implementations • 31 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.
2 code implementations • 8 Jul 2023 • David R. Johnson, Joyce A. Chew, Edward De Brouwer, Smita Krishnaswamy, Deanna Needell, Michael Perlmutter
In order to better understand manifold neural networks (MNNs), we introduce Manifold Filter-Combine Networks (MFCNs).
no code implementations • 13 Jun 2023 • Dhananjay Bhaskar, Sumner Magruder, Edward De Brouwer, Aarthi Venkat, Frederik Wenkel, Guy Wolf, Smita Krishnaswamy
Complex systems are characterized by intricate interactions between entities that evolve dynamically over time.
no code implementations • 5 Jun 2023 • Samuel Leone, Aarthi Venkat, Guillaume Huguet, Alexander Tong, Guy Wolf, Smita Krishnaswamy
GFMMD is defined via an optimal witness function that is both smooth on the graph and maximizes difference in expectation between the pair of distributions on the graph.
1 code implementation • 1 Jun 2023 • Oluwadamilola Fasina, Guillaume Huguet, Alexander Tong, Yanlei Zhang, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature.
1 code implementation • International Conference on Machine Learning Workshop on TAGML 2023 • Danqi Liao*, Chen Liu*, Alexander Tong, Guillaume Huguet, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
We also see that there is an increase in DSMI with the class label over time.
1 code implementation • NeurIPS 2023 • Guillaume Huguet, Alexander Tong, Edward De Brouwer, Yanlei Zhang, Guy Wolf, Ian Adelstein, Smita Krishnaswamy
Finally, we show that parameters of our more general method can be configured to give results similar to PHATE (a state-of-the-art diffusion based manifold learning method) as well as SNE (an attraction/repulsion neighborhood based method that forms the basis of t-SNE).
no code implementations • 2 Nov 2022 • Guillaume Huguet, Alexander Tong, María Ramos Zapatero, Christopher J. Tape, Guy Wolf, Smita Krishnaswamy
Efficient computation of optimal transport distance between distributions is of growing importance in data science.
3 code implementations • 23 Sep 2022 • Chen Liu, Matthew Amodio, Liangbo L. Shen, Feng Gao, Arman Avesta, Sanjay Aneja, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy
Segmenting medical images is critical to facilitating both patient diagnoses and quantitative research.
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 • 15 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.
no code implementations • 29 Jun 2022 • Guillaume Huguet, D. S. Magruder, Alexander Tong, Oluwadamilola Fasina, Manik Kuchroo, Guy Wolf, Smita Krishnaswamy
In GAE the latent space distance between points is regularized to match a novel multiscale geodesic distance on the data manifold that we define.
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.
no code implementations • 8 Jun 2022 • Dhananjay Bhaskar, Kincaid MacDonald, Oluwadamilola Fasina, Dawson Thomas, Bastian Rieck, Ian Adelstein, Smita Krishnaswamy
We introduce a new intrinsic measure of local curvature on point-cloud data called diffusion curvature.
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.
1 code implementation • 24 Jan 2022 • Egbert Castro, Abhinav Godavarthi, Julian Rubinfien, Kevin B. Givechian, Dhananjay Bhaskar, Smita Krishnaswamy
Using ReLSO, we explicitly model the sequence-function landscape of large labeled datasets and generate new molecules by optimizing within the latent space using gradient-based methods.
no code implementations • 22 Dec 2021 • Jessie Huang, Erica L. Busch, Tom Wallenstein, Michal Gerasimiuk, Andrew Benz, Guillaume Lajoie, Guy Wolf, Nicholas B. Turk-Browne, Smita Krishnaswamy
In order to understand the connection between stimuli of interest and brain activity, and analyze differences and commonalities between subjects, it becomes important to learn a meaningful embedding of the data that denoises, and reveals its intrinsic structure.
1 code implementation • 19 Nov 2021 • Michal Gerasimiuk, Dennis Shung, Alexander Tong, Adrian Stanley, Michael Schultz, Jeffrey Ngu, Loren Laine, Guy Wolf, Smita Krishnaswamy
In particular, in EHR data, some variables are {\em missing not at random (MNAR)} but deliberately not collected and thus are a source of information.
no code implementations • 12 Oct 2021 • Dhananjay Bhaskar, Jackson D. Grady, Michael A. Perlmutter, Smita Krishnaswamy
We guide the latent representation of an autoencoder by capturing graph structure information with the geometric scattering transform and apply penalties that structure the representation also by molecular properties.
no code implementations • 26 Jul 2021 • Alexander Tong, Guillaume Huguet, Dennis Shung, Amine Natik, Manik Kuchroo, Guillaume Lajoie, Guy Wolf, Smita Krishnaswamy
We propose to compare and organize such datasets of graph signals by using an earth mover's distance (EMD) with a geodesic cost over the underlying graph.
no code implementations • ICLR Workshop GTRL 2021 • Feng Gao, Jessica Moore, Bastian Rieck, Valentina Greco, Smita Krishnaswamy
However the function of calcium signaling in epithelial cells is not well understood.
1 code implementation • 25 Feb 2021 • Alexander Tong, Guillaume Huguet, Amine Natik, Kincaid MacDonald, Manik Kuchroo, Ronald Coifman, Guy Wolf, Smita Krishnaswamy
Here, Diffusion EMD can derive distances between patients on the manifold of cells at least two orders of magnitude faster than equally accurate methods.
no code implementations • 12 Feb 2021 • Manik Kuchroo, Abhinav Godavarthi, Alexander Tong, Guy Wolf, Smita Krishnaswamy
We propose a method called integrated diffusion for combining multimodal datasets, or data gathered via several different measurements on the same system, to create a joint data diffusion operator.
no code implementations • 31 Jan 2021 • Stefan Horoi, Jessie Huang, Bastian Rieck, Guillaume Lajoie, Guy Wolf, Smita Krishnaswamy
This suggests that qualitative and quantitative examination of the loss landscape geometry could yield insights about neural network generalization performance during training.
no code implementations • 6 Oct 2020 • Alexander Tong, Frederik Wenkel, Kincaid MacDonald, 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.
no code implementations • 23 Jun 2020 • Matthew Amodio, Rim Assouel, Victor Schmidt, Tristan Sylvain, Smita Krishnaswamy, Yoshua Bengio
Unsupervised image-to-image translation consists of learning a pair of mappings between two domains without known pairwise correspondences between points.
1 code implementation • NeurIPS 2020 • Bastian Rieck, Tristan Yates, Christian Bock, Karsten Borgwardt, Guy Wolf, Nicholas Turk-Browne, Smita Krishnaswamy
We observe significant differences in both brain state trajectories and overall topological activity between adults and children watching the same movie.
2 code implementations • 12 Jun 2020 • Egbert Castro, Andrew Benz, Alexander Tong, Guy Wolf, Smita Krishnaswamy
We propose a geometric scattering autoencoder (GSAE) network for learning such graph embeddings.
1 code implementation • 10 Feb 2020 • Tobias Brudermueller, Dennis L. Shung, Adrian J. Stanley, Johannes Stegmaier, Smita Krishnaswamy
We show the utility of our pipeline on a network that is trained on biomedical data.
2 code implementations • ICML 2020 • Alexander Tong, Jessie Huang, Guy Wolf, David van Dijk, Smita Krishnaswamy
To address this issue, we establish a link between continuous normalizing flows and dynamic optimal transport, that allows us to model the expected paths of points over time.
no code implementations • 25 Sep 2019 • Matthew Amodio, David van Dijk, Ruth Montgomery, Guy Wolf, Smita Krishnaswamy
While generative neural networks can learn to transform a specific input dataset into a specific target dataset, they require having just such a paired set of input/output datasets.
no code implementations • 25 Sep 2019 • Matthew Amodio, Smita Krishnaswamy
Generative adversarial networks (GANs) learn to map samples from a noise distribution to a chosen data distribution.
1 code implementation • NeurIPS 2019 • Scott Gigante, Adam S. Charles, Smita Krishnaswamy, Gal Mishne
We demonstrate M-PHATE with two vignettes: continual learning and generalization.
1 code implementation • 10 Jul 2019 • Nathan Brugnone, Alex Gonopolskiy, Mark W. Moyle, Manik Kuchroo, David van Dijk, Kevin R. Moon, Daniel Colon-Ramos, Guy Wolf, Matthew J. Hirn, Smita Krishnaswamy
Here, we consider multiple levels of abstraction via a multiresolution geometry of data points at different granularities.
no code implementations • 26 May 2019 • Alexander Tong, Guy Wolf, Smita Krishnaswamy
We show that this procedure successfully detects unseen anomalies with guarantees on those that have a certain Wasserstein distance from the data or corrupted training set.
no code implementations • ICLR 2019 • Alexander Tong, David van Dijk, Jay Stanley, Guy Wolf, Smita Krishnaswamy
First, we show a synthetic example that the graph-structured layer can reveal topological features of the data.
no code implementations • ICLR 2019 • Jay S. Stanley III, Guy Wolf, Smita Krishnaswamy
We leverage this assumption to estimate relations between intrinsic manifold dimensions, which are given by diffusion map coordinates over each of the datasets.
no code implementations • ICLR Workshop LLD 2019 • Daniel B. Burkhardt, Jay S. Stanley III, Ana Luisa Perdigoto, Scott A. Gigante, Kevan C. Herold, Guy Wolf, Antonio J. Giraldez, David van Dijk, Smita Krishnaswamy
Single-cell RNA-sequencing (scRNA-seq) is a powerful tool for analyzing biological systems.
2 code implementations • CVPR 2019 • Matthew Amodio, Smita Krishnaswamy
The achievements of these models have been limited to a particular subset of domains where this assumption yields good results, namely homogeneous domains that are characterized by style or texture differences.
no code implementations • 31 Jan 2019 • Scott Gigante, Jay S. Stanley III, Ngan Vu, David van Dijk, Kevin Moon, Guy Wolf, Smita Krishnaswamy
Diffusion maps are a commonly used kernel-based method for manifold learning, which can reveal intrinsic structures in data and embed them in low dimensions.
1 code implementation • 25 Jan 2019 • David van Dijk, Daniel Burkhardt, Matthew Amodio, Alex Tong, Guy Wolf, Smita Krishnaswamy
Here, we propose a reformulation of the problem such that the goal is to learn a non-linear transformation of the data into a latent archetypal space.
no code implementations • 24 Jan 2019 • Matthew Amodio, Smita Krishnaswamy
Unsupervised domain mapping has attracted substantial attention in recent years due to the success of models based on the cycle-consistency assumption.
no code implementations • NeurIPS 2018 • Ofir Lindenbaum, Jay Stanley, Guy Wolf, Smita Krishnaswamy
We propose a new type of generative model for high-dimensional data that learns a manifold geometry of the data, rather than density, and can generate points evenly along this manifold.
no code implementations • 30 Sep 2018 • Jay S. Stanley III, Scott Gigante, Guy Wolf, Smita Krishnaswamy
We use this to relate the diffusion coordinates of each dataset through our assumption of partial feature correspondence.
1 code implementation • ICLR 2019 • Alexander Tong, David van Dijk, Jay S. Stanley III, Matthew Amodio, Kristina Yim, Rebecca Muhle, James Noonan, Guy Wolf, Smita Krishnaswamy
Taking inspiration from spatial organization and localization of neuron activations in biological networks, we use a graph Laplacian penalty to structure the activations within a layer.
no code implementations • 27 Sep 2018 • Scott Gigante, David van Dijk, Kevin R. Moon, Alexander Strzalkowski, Katie Ferguson, Guy Wolf, Smita Krishnaswamy
DyMoN is well-suited to the idiosyncrasies of biological data, including noise, sparsity, and the lack of longitudinal measurements in many types of systems.
1 code implementation • 14 Feb 2018 • Ofir Lindenbaum, Jay S. Stanley III, Guy Wolf, Smita Krishnaswamy
Then, it generates new points evenly along the manifold by pulling randomly generated points into its intrinsic structure using a diffusion kernel.
1 code implementation • ICML 2018 • Matthew Amodio, Smita Krishnaswamy
We present a new GAN called the Manifold-Aligning GAN (MAGAN) that aligns two manifolds such that related points in each measurement space are aligned together.
no code implementations • 10 Feb 2018 • Scott Gigante, David van Dijk, Kevin Moon, Alexander Strzalkowski, Guy Wolf, Smita Krishnaswamy
In order to model the dynamics of such systems given snapshot data, or local transitions, we present a deep neural network framework we call Dynamics Modeling Network or DyMoN.