In this paper, we propose Graph Differential Equation Network (GDeNet), ...
We present simulation-free score and flow matching ([SF]^2M), a
simulati...
Complex systems are characterized by intricate interactions between enti...
While numerous methods have been proposed for computing distances betwee...
Diffusion-based manifold learning methods have proven useful in
represen...
Continuous normalizing flows (CNFs) are an attractive generative modelin...
Understanding the dynamics and reactions of cells from population snapsh...
Comparing learned neural representations in neural networks is a challen...
Multi-domain data is becoming increasingly common and presents both
chal...
We propose a new graph neural network (GNN) module, based on relaxations...
Here, we present a method called Manifold Interpolating Optimal-Transpor...
Graph Neural Networks (GNNs) extend the success of neural networks to
gr...
The integration of multimodal data presents a challenge in cases when th...
We propose a geometric scattering-based graph neural network (GNN) for
a...
Diffusion condensation is a dynamic process that yields a sequence of
mu...
Geometric deep learning (GDL) has made great strides towards generalizin...
A major challenge in embedding or visualizing clinical patient data is t...
Positivity is one of the three conditions for causal inference from
obse...
Graph neural networks (GNNs) have attracted much attention due to their
...
In modern relational machine learning it is common to encounter large gr...
The wavelet scattering transform creates geometric invariants and deform...
Graph neural networks (GNNs) based on message passing between neighborin...
We propose a new fast method of measuring distances between large number...
We propose a method called integrated diffusion for combining multimodal...
Training artificial neural networks requires the optimization of highly
...
Geometric scattering has recently gained recognition in graph representa...
Graph neural networks (GNNs) in general, and graph convolutional network...
A fundamental task in data exploration is to extract simplified low
dime...
Dynamic adaptation in single-neuron response plays a fundamental role in...
Dimensionality reduction is often used as an initial step in data
explor...
Functional magnetic resonance imaging (fMRI) is a crucial technology for...
Biomolecular graph analysis has recently gained much attention in the
em...
Graph convolutional networks (GCNs) have shown promising results in
proc...
We introduce a novel approach to optimize the architecture of deep neura...
It is increasingly common to encounter data from dynamic processes captu...
The efficiency of recurrent neural networks (RNNs) in dealing with seque...
The scattering transform is a multilayered wavelet-based deep learning
a...
Big data often has emergent structure that exists at multiple levels of
...
Manifold learning techniques for dynamical systems and time series have ...
Anomaly detection is a problem of great interest in medicine, finance, a...
The Euclidean scattering transform was introduced nearly a decade ago to...
Diffusion maps are a commonly used kernel-based method for manifold lear...
Archetypal analysis is a type of factor analysis where data is fit by a
...
We present a mathematical model for geometric deep learning based upon a...
One of the most notable contributions of deep learning is the applicatio...
Deep neural networks can learn meaningful representations of data. Howev...
We propose a novel framework for combining datasets via alignment of the...
Many generative models attempt to replicate the density of their input d...
Markov processes, both classical and higher order, are often used to mod...
Diffusion Maps framework is a kernel based method for manifold learning ...