78 citations · 215 across the 52 of their papers we have counts for
26 papers · 1 filter
RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
Yali Fink, Ido Ben-Yair, Lars Ruthotto +1
The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis. While algebraic multigrid (AMG) offers optimal linear scaling, its…
Understanding and Improving Laplacian Positional Encodings For Temporal GNNs
Yaniv Galron, Fabrizio Frasca, Haggai Maron +2
Temporal graph learning has applications in recommendation systems, traffic forecasting, and social network analysis. Although multiple architectures have been introduced, progress…
Improving the Effective Receptive Field of Message-Passing Neural Networks
Shahaf E. Finder, Ron Shapira Weber, Moshe Eliasof +2
Message-Passing Neural Networks (MPNNs) have become a cornerstone for processing and analyzing graph-structured data. However, their effectiveness is often hindered by phenomena su…
Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
Eshed Gal, Moshe Eliasof, Carola-Bibiane Schönlieb +3
Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data, finding applications across diverse domains. However, as graph sizes and connectivi…
Graph Neural Reaction Diffusion Models
Moshe Eliasof, Eldad Haber, Eran Treister
The integration of Graph Neural Networks (GNNs) and Neural Ordinary and Partial Differential Equations has been extensively studied in recent years. GNN architectures powered by ne…
Global-Local Graph Neural Networks for Node-Classification
Moshe Eliasof, Eran Treister
The task of graph node classification is often approached by utilizing a local Graph Neural Network (GNN), that learns only local information from the node input features and their…
Physics-guided Full Waveform Inversion using Encoder-Solver Convolutional Neural Networks
Matan Goren, Eran Treister
Full Waveform Inversion (FWI) is an inverse problem for estimating the wave velocity distribution in a given domain, based on observed data on the boundaries. The inversion is comp…
An Over Complete Deep Learning Method for Inverse Problems
Moshe Eliasof, Eldad Haber, Eran Treister
Obtaining meaningful solutions for inverse problems has been a major challenge with many applications in science and engineering. Recent machine learning techniques based on proxim…
On The Temporal Domain of Differential Equation Inspired Graph Neural Networks
Moshe Eliasof, Eldad Haber, Eran Treister +1
Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling complex relationships in graph-structured data. A recent innovation in this field is the family of Dif…
Feature Transportation Improves Graph Neural Networks
Moshe Eliasof, Eldad Haber, Eran Treister
Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data. However, GNNs still face challenges in modeling complex phenomena…
Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation using Compact Implicit Layers
Bar Lerer, Ido Ben-Yair, Eran Treister
We present a deep learning-based iterative approach to solve the discrete heterogeneous Helmholtz equation for high wavenumbers. Combining classical iterative multigrid solvers and…
DRIP: Deep Regularizers for Inverse Problems
Moshe Eliasof, Eldad Haber, Eran Treister
In this paper we consider inverse problems that are mathematically ill-posed. That is, given some (noisy) data, there is more than one solution that approximately fits the data. In…
Graph Positional Encoding via Random Feature Propagation
Moshe Eliasof, Fabrizio Frasca, Beatrice Bevilacqua +3
Two main families of node feature augmentation schemes have been explored for enhancing GNNs: random features and spectral positional encoding. Surprisingly, however, there is stil…
Efficient Graph Laplacian Estimation by Proximal Newton
Yakov Medvedovsky, Eran Treister, Tirza Routtenberg
The Laplacian-constrained Gaussian Markov Random Field (LGMRF) is a common multivariate statistical model for learning a weighted sparse dependency graph from given data. This grap…
NeRN -- Learning Neural Representations for Neural Networks
Maor Ashkenazi, Zohar Rimon, Ron Vainshtein +4
Neural Representations have recently been shown to effectively reconstruct a wide range of signals from 3D meshes and shapes to images and videos. We show that, when adapted correc…
Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification
Moshe Eliasof, Eldad Haber, Eran Treister
Graph Neural Networks (GNNs) are prominent in handling sparse and unstructured data efficiently and effectively. Specifically, GNNs were shown to be highly effective for node class…
Improving Graph Neural Networks with Learnable Propagation Operators
Moshe Eliasof, Lars Ruthotto, Eran Treister
Graph Neural Networks (GNNs) are limited in their propagation operators. In many cases, these operators often contain non-negative elements only and are shared across channels, lim…
pathGCN: Learning General Graph Spatial Operators from Paths
Moshe Eliasof, Eldad Haber, Eran Treister
Graph Convolutional Networks (GCNs), similarly to Convolutional Neural Networks (CNNs), are typically based on two main operations - spatial and point-wise convolutions. In the con…
Disparate Conditional Prediction in Multiclass Classifiers
Sivan Sabato, Eran Treister, Elad Yom-Tov
We propose methods for auditing multiclass classifiers for fairness under multiclass equalized odds,by estimating the deviation from equalized odds when the classifier is not compl…
Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations
Ido Ben-Yair, Gil Ben Shalom, Moshe Eliasof +1
Quantization of Convolutional Neural Networks (CNNs) is a common approach to ease the computational burden involved in the deployment of CNNs, especially on low-resource edge devic…
PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
Moshe Eliasof, Eldad Haber, Eran Treister
Graph neural networks are increasingly becoming the go-to approach in various fields such as computer vision, computational biology and chemistry, where data are naturally explaine…
GradFreeBits: Gradient Free Bit Allocation for Dynamic Low Precision Neural Networks
Benjamin J. Bodner, Gil Ben Shalom, Eran Treister
Quantized neural networks (QNNs) are among the main approaches for deploying deep neural networks on low resource edge devices. Training QNNs using different levels of precision th…
Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks
Jonathan Ephrath, Lars Ruthotto, Eran Treister
We present a multigrid approach that combats the quadratic growth of the number of parameters with respect to the number of channels in standard convolutional neural networks (CNNs…
Effective Learning of a GMRF Mixture Model
Shahaf E. Finder, Eran Treister, Oren Freifeld
Learning a Gaussian Mixture Model (GMM) is hard when the number of parameters is too large given the amount of available data. As a remedy, we propose restricting the GMM to a Gaus…